Logging to logs/HalfCheetah-v4/exp-1/maxentirl/2024_05_12_19_18_02
-2024-05-12 19:19:43.735637 ʱ--
| Itration            | 0         |
| Loss                | 20.7      |
| Real Det Return     | -1.63e+03 |
| Real Sto Return     | -1.57e+03 |
| Running Env Steps   | 0         |
| Running Forward KL  | 39.9      |
| Running Reverse KL  | 8.27      |
| Running Update Time | 0         |
-----------------------------------
-2024-05-12 19:21:38.521010 ʱ--
| Itration            | 1         |
| Loss                | 332       |
| Real Det Return     | -414      |
| Real Sto Return     | -1.02e+03 |
| Running Env Steps   | 5000      |
| Running Forward KL  | 38.1      |
| Running Reverse KL  | 6.49      |
| Running Update Time | 1         |
-----------------------------------
-2024-05-12 19:23:33.528766 ʱ--
| Itration            | 2         |
| Loss                | -77.2     |
| Real Det Return     | -1.13e+03 |
| Real Sto Return     | -1.14e+03 |
| Running Env Steps   | 10000     |
| Running Forward KL  | 39.5      |
| Running Reverse KL  | 8.39      |
| Running Update Time | 2         |
-----------------------------------
-2024-05-12 19:25:28.670710 ʱ-
| Itration            | 3        |
| Loss                | -315     |
| Real Det Return     | -774     |
| Real Sto Return     | -812     |
| Running Env Steps   | 15000    |
| Running Forward KL  | 39       |
| Running Reverse KL  | 6.9      |
| Running Update Time | 3        |
----------------------------------
-2024-05-12 19:27:23.282633 ʱ--
| Itration            | 4         |
| Loss                | -42.7     |
| Real Det Return     | -1.02e+03 |
| Real Sto Return     | -537      |
| Running Env Steps   | 20000     |
| Running Forward KL  | 39.1      |
| Running Reverse KL  | 7.24      |
| Running Update Time | 4         |
-----------------------------------
-2024-05-12 19:29:18.116878 ʱ--
| Itration            | 5         |
| Loss                | 44.8      |
| Real Det Return     | -1.43e+03 |
| Real Sto Return     | -717      |
| Running Env Steps   | 25000     |
| Running Forward KL  | 38.8      |
| Running Reverse KL  | 8.69      |
| Running Update Time | 5         |
-----------------------------------
-2024-05-12 19:31:14.722662 ʱ--
| Itration            | 6         |
| Loss                | 11.6      |
| Real Det Return     | -1.78e+03 |
| Real Sto Return     | -921      |
| Running Env Steps   | 30000     |
| Running Forward KL  | 39        |
| Running Reverse KL  | 8.3       |
| Running Update Time | 6         |
-----------------------------------
-2024-05-12 19:33:09.487409 ʱ--
| Itration            | 7         |
| Loss                | -34.8     |
| Real Det Return     | -1.78e+03 |
| Real Sto Return     | -1.06e+03 |
| Running Env Steps   | 35000     |
| Running Forward KL  | 39.7      |
| Running Reverse KL  | 8.24      |
| Running Update Time | 7         |
-----------------------------------
-2024-05-12 19:35:11.094292 ʱ--
| Itration            | 8         |
| Loss                | -303      |
| Real Det Return     | -2.75e+03 |
| Real Sto Return     | -1.31e+03 |
| Running Env Steps   | 40000     |
| Running Forward KL  | 40.3      |
| Running Reverse KL  | 8.47      |
| Running Update Time | 8         |
-----------------------------------
-2024-05-12 19:37:05.633308 ʱ--
| Itration            | 9         |
| Loss                | 13.6      |
| Real Det Return     | -2.25e+03 |
| Real Sto Return     | -1.26e+03 |
| Running Env Steps   | 45000     |
| Running Forward KL  | 40.1      |
| Running Reverse KL  | 9.3       |
| Running Update Time | 9         |
-----------------------------------
-2024-05-12 19:39:00.987203 ʱ--
| Itration            | 10        |
| Loss                | -372      |
| Real Det Return     | -2.2e+03  |
| Real Sto Return     | -1.48e+03 |
| Running Env Steps   | 50000     |
| Running Forward KL  | 40.1      |
| Running Reverse KL  | 7.89      |
| Running Update Time | 10        |
-----------------------------------
-2024-05-12 19:40:57.306438 ʱ--
| Itration            | 11        |
| Loss                | 2.53      |
| Real Det Return     | -2.49e+03 |
| Real Sto Return     | -1.63e+03 |
| Running Env Steps   | 55000     |
| Running Forward KL  | 40        |
| Running Reverse KL  | 10        |
| Running Update Time | 11        |
-----------------------------------
-2024-05-12 19:42:55.268492 ʱ--
| Itration            | 12        |
| Loss                | 27.7      |
| Real Det Return     | -2.66e+03 |
| Real Sto Return     | -2.01e+03 |
| Running Env Steps   | 60000     |
| Running Forward KL  | 40.6      |
| Running Reverse KL  | 10.5      |
| Running Update Time | 12        |
-----------------------------------
-2024-05-12 19:44:53.754261 ʱ--
| Itration            | 13        |
| Loss                | -2.52     |
| Real Det Return     | -2.76e+03 |
| Real Sto Return     | -1.97e+03 |
| Running Env Steps   | 65000     |
| Running Forward KL  | 40.6      |
| Running Reverse KL  | 9.84      |
| Running Update Time | 13        |
-----------------------------------
-2024-05-12 19:46:55.192977 ʱ--
| Itration            | 14        |
| Loss                | 0.336     |
| Real Det Return     | -3.06e+03 |
| Real Sto Return     | -2.16e+03 |
| Running Env Steps   | 70000     |
| Running Forward KL  | 41.2      |
| Running Reverse KL  | 10.1      |
| Running Update Time | 14        |
-----------------------------------
-2024-05-12 19:49:01.168425 ʱ--
| Itration            | 15        |
| Loss                | 43.3      |
| Real Det Return     | -3.32e+03 |
| Real Sto Return     | -2.35e+03 |
| Running Env Steps   | 75000     |
| Running Forward KL  | 40.8      |
| Running Reverse KL  | 10.5      |
| Running Update Time | 15        |
-----------------------------------
-2024-05-12 19:51:08.968542 ʱ--
| Itration            | 16        |
| Loss                | -7.66     |
| Real Det Return     | -3.17e+03 |
| Real Sto Return     | -2.33e+03 |
| Running Env Steps   | 80000     |
| Running Forward KL  | 40.8      |
| Running Reverse KL  | 11        |
| Running Update Time | 16        |
-----------------------------------
-2024-05-12 19:53:17.808958 ʱ--
| Itration            | 17        |
| Loss                | -39.6     |
| Real Det Return     | -2.46e+03 |
| Real Sto Return     | -2.09e+03 |
| Running Env Steps   | 85000     |
| Running Forward KL  | 40.8      |
| Running Reverse KL  | 10        |
| Running Update Time | 17        |
-----------------------------------
-2024-05-12 19:55:27.211991 ʱ--
| Itration            | 18        |
| Loss                | -54.3     |
| Real Det Return     | -3.43e+03 |
| Real Sto Return     | -2.51e+03 |
| Running Env Steps   | 90000     |
| Running Forward KL  | 41.2      |
| Running Reverse KL  | 10.9      |
| Running Update Time | 18        |
-----------------------------------
-2024-05-12 19:57:37.777583 ʱ--
| Itration            | 19        |
| Loss                | 44.6      |
| Real Det Return     | -3.36e+03 |
| Real Sto Return     | -2.62e+03 |
| Running Env Steps   | 95000     |
| Running Forward KL  | 40.9      |
| Running Reverse KL  | 11.3      |
| Running Update Time | 19        |
-----------------------------------
-2024-05-12 19:59:48.208461 ʱ--
| Itration            | 20        |
| Loss                | 237       |
| Real Det Return     | -3.49e+03 |
| Real Sto Return     | -2.6e+03  |
| Running Env Steps   | 100000    |
| Running Forward KL  | 42        |
| Running Reverse KL  | 11.5      |
| Running Update Time | 20        |
-----------------------------------
-2024-05-12 20:01:59.240336 ʱ--
| Itration            | 21        |
| Loss                | -1.16e+03 |
| Real Det Return     | -3.53e+03 |
| Real Sto Return     | -2.62e+03 |
| Running Env Steps   | 105000    |
| Running Forward KL  | 40.3      |
| Running Reverse KL  | 9.53      |
| Running Update Time | 21        |
-----------------------------------
-2024-05-12 20:04:11.015797 ʱ--
| Itration            | 22        |
| Loss                | -15.3     |
| Real Det Return     | -3.47e+03 |
| Real Sto Return     | -2.83e+03 |
| Running Env Steps   | 110000    |
| Running Forward KL  | 41.3      |
| Running Reverse KL  | 11.7      |
| Running Update Time | 22        |
-----------------------------------
-2024-05-12 20:06:22.196938 ʱ--
| Itration            | 23        |
| Loss                | -31.3     |
| Real Det Return     | -3.79e+03 |
| Real Sto Return     | -2.83e+03 |
| Running Env Steps   | 115000    |
| Running Forward KL  | 41.3      |
| Running Reverse KL  | 11.2      |
| Running Update Time | 23        |
-----------------------------------
-2024-05-12 20:08:33.883997 ʱ--
| Itration            | 24        |
| Loss                | 3.4       |
| Real Det Return     | -3.82e+03 |
| Real Sto Return     | -2.93e+03 |
| Running Env Steps   | 120000    |
| Running Forward KL  | 41.8      |
| Running Reverse KL  | 11.3      |
| Running Update Time | 24        |
-----------------------------------
-2024-05-12 20:10:46.909119 ʱ--
| Itration            | 25        |
| Loss                | -4.83     |
| Real Det Return     | -3.6e+03  |
| Real Sto Return     | -2.83e+03 |
| Running Env Steps   | 125000    |
| Running Forward KL  | 41.8      |
| Running Reverse KL  | 11.8      |
| Running Update Time | 25        |
-----------------------------------
-2024-05-12 20:12:59.993881 ʱ--
| Itration            | 26        |
| Loss                | -73.5     |
| Real Det Return     | -3.64e+03 |
| Real Sto Return     | -2.99e+03 |
| Running Env Steps   | 130000    |
| Running Forward KL  | 41.5      |
| Running Reverse KL  | 10.9      |
| Running Update Time | 26        |
-----------------------------------
-2024-05-12 20:15:13.649860 ʱ--
| Itration            | 27        |
| Loss                | 87.1      |
| Real Det Return     | -4.22e+03 |
| Real Sto Return     | -2.95e+03 |
| Running Env Steps   | 135000    |
| Running Forward KL  | 42.1      |
| Running Reverse KL  | 12.9      |
| Running Update Time | 27        |
-----------------------------------
-2024-05-12 20:17:26.824192 ʱ--
| Itration            | 28        |
| Loss                | 6.34      |
| Real Det Return     | -3.54e+03 |
| Real Sto Return     | -2.83e+03 |
| Running Env Steps   | 140000    |
| Running Forward KL  | 41.4      |
| Running Reverse KL  | 11.5      |
| Running Update Time | 28        |
-----------------------------------
-2024-05-12 20:19:40.139308 ʱ--
| Itration            | 29        |
| Loss                | 45.1      |
| Real Det Return     | -3.51e+03 |
| Real Sto Return     | -3.04e+03 |
| Running Env Steps   | 145000    |
| Running Forward KL  | 42        |
| Running Reverse KL  | 12.5      |
| Running Update Time | 29        |
-----------------------------------
-2024-05-12 20:21:53.691353 ʱ--
| Itration            | 30        |
| Loss                | -1.6      |
| Real Det Return     | -3.61e+03 |
| Real Sto Return     | -2.99e+03 |
| Running Env Steps   | 150000    |
| Running Forward KL  | 41.7      |
| Running Reverse KL  | 11.8      |
| Running Update Time | 30        |
-----------------------------------
-2024-05-12 20:24:07.250872 ʱ--
| Itration            | 31        |
| Loss                | 28        |
| Real Det Return     | -3.86e+03 |
| Real Sto Return     | -3.07e+03 |
| Running Env Steps   | 155000    |
| Running Forward KL  | 42.3      |
| Running Reverse KL  | 12        |
| Running Update Time | 31        |
-----------------------------------
-2024-05-12 20:26:22.657004 ʱ--
| Itration            | 32        |
| Loss                | -12.2     |
| Real Det Return     | -4.02e+03 |
| Real Sto Return     | -3.17e+03 |
| Running Env Steps   | 160000    |
| Running Forward KL  | 41.9      |
| Running Reverse KL  | 11.3      |
| Running Update Time | 32        |
-----------------------------------
-2024-05-12 20:28:35.913616 ʱ--
| Itration            | 33        |
| Loss                | 16        |
| Real Det Return     | -3.99e+03 |
| Real Sto Return     | -3.13e+03 |
| Running Env Steps   | 165000    |
| Running Forward KL  | 42.5      |
| Running Reverse KL  | 12.2      |
| Running Update Time | 33        |
-----------------------------------
-2024-05-12 20:30:51.466296 ʱ--
| Itration            | 34        |
| Loss                | 60.9      |
| Real Det Return     | -3.94e+03 |
| Real Sto Return     | -3.16e+03 |
| Running Env Steps   | 170000    |
| Running Forward KL  | 43        |
| Running Reverse KL  | 12.7      |
| Running Update Time | 34        |
-----------------------------------
-2024-05-12 20:33:05.203561 ʱ--
| Itration            | 35        |
| Loss                | 35.9      |
| Real Det Return     | -3.85e+03 |
| Real Sto Return     | -3.14e+03 |
| Running Env Steps   | 175000    |
| Running Forward KL  | 42.8      |
| Running Reverse KL  | 12.5      |
| Running Update Time | 35        |
-----------------------------------
-2024-05-12 20:35:18.626484 ʱ--
| Itration            | 36        |
| Loss                | 10.8      |
| Real Det Return     | -3.76e+03 |
| Real Sto Return     | -3.24e+03 |
| Running Env Steps   | 180000    |
| Running Forward KL  | 42.6      |
| Running Reverse KL  | 12.6      |
| Running Update Time | 36        |
-----------------------------------
-2024-05-12 20:37:32.320848 ʱ--
| Itration            | 37        |
| Loss                | 35.5      |
| Real Det Return     | -3.87e+03 |
| Real Sto Return     | -3.19e+03 |
| Running Env Steps   | 185000    |
| Running Forward KL  | 42.4      |
| Running Reverse KL  | 12.1      |
| Running Update Time | 37        |
-----------------------------------
-2024-05-12 20:39:45.774754 ʱ--
| Itration            | 38        |
| Loss                | 19.6      |
| Real Det Return     | -3.88e+03 |
| Real Sto Return     | -3.12e+03 |
| Running Env Steps   | 190000    |
| Running Forward KL  | 42.3      |
| Running Reverse KL  | 11.8      |
| Running Update Time | 38        |
-----------------------------------
-2024-05-12 20:41:59.347489 ʱ--
| Itration            | 39        |
| Loss                | -19.8     |
| Real Det Return     | -3.76e+03 |
| Real Sto Return     | -3.02e+03 |
| Running Env Steps   | 195000    |
| Running Forward KL  | 42.1      |
| Running Reverse KL  | 11.8      |
| Running Update Time | 39        |
-----------------------------------
-2024-05-12 20:44:13.449141 ʱ--
| Itration            | 40        |
| Loss                | 53.3      |
| Real Det Return     | -3.75e+03 |
| Real Sto Return     | -3.15e+03 |
| Running Env Steps   | 200000    |
| Running Forward KL  | 42.7      |
| Running Reverse KL  | 12.4      |
| Running Update Time | 40        |
-----------------------------------
-2024-05-12 20:46:27.814344 ʱ--
| Itration            | 41        |
| Loss                | 36.7      |
| Real Det Return     | -4.23e+03 |
| Real Sto Return     | -3.11e+03 |
| Running Env Steps   | 205000    |
| Running Forward KL  | 42.2      |
| Running Reverse KL  | 12.2      |
| Running Update Time | 41        |
-----------------------------------
-2024-05-12 20:48:41.665585 ʱ--
| Itration            | 42        |
| Loss                | 38.1      |
| Real Det Return     | -3.89e+03 |
| Real Sto Return     | -3.1e+03  |
| Running Env Steps   | 210000    |
| Running Forward KL  | 42.4      |
| Running Reverse KL  | 12.6      |
| Running Update Time | 42        |
-----------------------------------
-2024-05-12 20:50:56.360040 ʱ--
| Itration            | 43        |
| Loss                | -18.2     |
| Real Det Return     | -3.71e+03 |
| Real Sto Return     | -3.2e+03  |
| Running Env Steps   | 215000    |
| Running Forward KL  | 42.6      |
| Running Reverse KL  | 11.5      |
| Running Update Time | 43        |
-----------------------------------
-2024-05-12 20:53:10.058029 ʱ--
| Itration            | 44        |
| Loss                | 60.3      |
| Real Det Return     | -3.18e+03 |
| Real Sto Return     | -2.85e+03 |
| Running Env Steps   | 220000    |
| Running Forward KL  | 41        |
| Running Reverse KL  | 11.7      |
| Running Update Time | 44        |
-----------------------------------
-2024-05-12 20:55:24.460971 ʱ--
| Itration            | 45        |
| Loss                | 13.6      |
| Real Det Return     | -3.99e+03 |
| Real Sto Return     | -3.17e+03 |
| Running Env Steps   | 225000    |
| Running Forward KL  | 41.8      |
| Running Reverse KL  | 11.8      |
| Running Update Time | 45        |
-----------------------------------
-2024-05-12 20:57:39.044820 ʱ--
| Itration            | 46        |
| Loss                | -5.73     |
| Real Det Return     | -3.92e+03 |
| Real Sto Return     | -3.31e+03 |
| Running Env Steps   | 230000    |
| Running Forward KL  | 42.9      |
| Running Reverse KL  | 11.7      |
| Running Update Time | 46        |
-----------------------------------
-2024-05-12 20:59:53.681481 ʱ--
| Itration            | 47        |
| Loss                | 35.7      |
| Real Det Return     | -4.42e+03 |
| Real Sto Return     | -3.04e+03 |
| Running Env Steps   | 235000    |
| Running Forward KL  | 42.2      |
| Running Reverse KL  | 11.7      |
| Running Update Time | 47        |
-----------------------------------
-2024-05-12 21:02:08.377208 ʱ--
| Itration            | 48        |
| Loss                | 36.7      |
| Real Det Return     | -3.77e+03 |
| Real Sto Return     | -3.26e+03 |
| Running Env Steps   | 240000    |
| Running Forward KL  | 42.8      |
| Running Reverse KL  | 12.4      |
| Running Update Time | 48        |
-----------------------------------
-2024-05-12 21:04:22.851671 ʱ--
| Itration            | 49        |
| Loss                | -13.8     |
| Real Det Return     | -4.18e+03 |
| Real Sto Return     | -3.34e+03 |
| Running Env Steps   | 245000    |
| Running Forward KL  | 42.2      |
| Running Reverse KL  | 11.8      |
| Running Update Time | 49        |
-----------------------------------
-2024-05-12 21:06:37.136333 ʱ--
| Itration            | 50        |
| Loss                | 65.3      |
| Real Det Return     | -4.21e+03 |
| Real Sto Return     | -3.12e+03 |
| Running Env Steps   | 250000    |
| Running Forward KL  | 42.7      |
| Running Reverse KL  | 12.4      |
| Running Update Time | 50        |
-----------------------------------
-2024-05-12 21:08:52.057624 ʱ--
| Itration            | 51        |
| Loss                | 27.3      |
| Real Det Return     | -4.06e+03 |
| Real Sto Return     | -3.3e+03  |
| Running Env Steps   | 255000    |
| Running Forward KL  | 42.6      |
| Running Reverse KL  | 12.3      |
| Running Update Time | 51        |
-----------------------------------
-2024-05-12 21:11:06.619304 ʱ--
| Itration            | 52        |
| Loss                | 30.8      |
| Real Det Return     | -4.31e+03 |
| Real Sto Return     | -3.5e+03  |
| Running Env Steps   | 260000    |
| Running Forward KL  | 43.5      |
| Running Reverse KL  | 12.1      |
| Running Update Time | 52        |
-----------------------------------
-2024-05-12 21:13:21.551863 ʱ--
| Itration            | 53        |
| Loss                | 17.4      |
| Real Det Return     | -4.58e+03 |
| Real Sto Return     | -3.57e+03 |
| Running Env Steps   | 265000    |
| Running Forward KL  | 43.1      |
| Running Reverse KL  | 12.1      |
| Running Update Time | 53        |
-----------------------------------
-2024-05-12 21:15:36.799267 ʱ--
| Itration            | 54        |
| Loss                | 14.3      |
| Real Det Return     | -4.33e+03 |
| Real Sto Return     | -3.45e+03 |
| Running Env Steps   | 270000    |
| Running Forward KL  | 43.6      |
| Running Reverse KL  | 12.1      |
| Running Update Time | 54        |
-----------------------------------
-2024-05-12 21:17:50.926997 ʱ--
| Itration            | 55        |
| Loss                | 35.7      |
| Real Det Return     | -3.88e+03 |
| Real Sto Return     | -3.44e+03 |
| Running Env Steps   | 275000    |
| Running Forward KL  | 42.8      |
| Running Reverse KL  | 11.8      |
| Running Update Time | 55        |
-----------------------------------
-2024-05-12 21:20:05.824859 ʱ--
| Itration            | 56        |
| Loss                | 53.5      |
| Real Det Return     | -4.54e+03 |
| Real Sto Return     | -3.46e+03 |
| Running Env Steps   | 280000    |
| Running Forward KL  | 43        |
| Running Reverse KL  | 12.3      |
| Running Update Time | 56        |
-----------------------------------
-2024-05-12 21:22:20.261497 ʱ--
| Itration            | 57        |
| Loss                | 23.7      |
| Real Det Return     | -4.16e+03 |
| Real Sto Return     | -3.32e+03 |
| Running Env Steps   | 285000    |
| Running Forward KL  | 42.9      |
| Running Reverse KL  | 12        |
| Running Update Time | 57        |
-----------------------------------
-2024-05-12 21:24:36.545255 ʱ--
| Itration            | 58        |
| Loss                | 61.9      |
| Real Det Return     | -4.27e+03 |
| Real Sto Return     | -3.46e+03 |
| Running Env Steps   | 290000    |
| Running Forward KL  | 42.7      |
| Running Reverse KL  | 12.4      |
| Running Update Time | 58        |
-----------------------------------
-2024-05-12 21:26:51.890897 ʱ--
| Itration            | 59        |
| Loss                | 38.3      |
| Real Det Return     | -4.13e+03 |
| Real Sto Return     | -3.35e+03 |
| Running Env Steps   | 295000    |
| Running Forward KL  | 42.4      |
| Running Reverse KL  | 11.8      |
| Running Update Time | 59        |
-----------------------------------
-2024-05-12 21:29:07.129075 ʱ--
| Itration            | 60        |
| Loss                | 27.3      |
| Real Det Return     | -4.4e+03  |
| Real Sto Return     | -3.53e+03 |
| Running Env Steps   | 300000    |
| Running Forward KL  | 43        |
| Running Reverse KL  | 12.5      |
| Running Update Time | 60        |
-----------------------------------
-2024-05-12 21:31:22.729514 ʱ--
| Itration            | 61        |
| Loss                | 52.3      |
| Real Det Return     | -4.35e+03 |
| Real Sto Return     | -3.48e+03 |
| Running Env Steps   | 305000    |
| Running Forward KL  | 43.6      |
| Running Reverse KL  | 12.3      |
| Running Update Time | 61        |
-----------------------------------
-2024-05-12 21:33:51.759520 ʱ--
| Itration            | 62        |
| Loss                | 56.3      |
| Real Det Return     | -4.11e+03 |
| Real Sto Return     | -3.46e+03 |
| Running Env Steps   | 310000    |
| Running Forward KL  | 42.9      |
| Running Reverse KL  | 11.9      |
| Running Update Time | 62        |
-----------------------------------
-2024-05-12 21:36:24.331318 ʱ--
| Itration            | 63        |
| Loss                | 2.18      |
| Real Det Return     | -4e+03    |
| Real Sto Return     | -3.46e+03 |
| Running Env Steps   | 315000    |
| Running Forward KL  | 42.6      |
| Running Reverse KL  | 12.1      |
| Running Update Time | 63        |
-----------------------------------
-2024-05-12 21:38:45.743773 ʱ--
| Itration            | 64        |
| Loss                | 19.1      |
| Real Det Return     | -4.08e+03 |
| Real Sto Return     | -3.45e+03 |
| Running Env Steps   | 320000    |
| Running Forward KL  | 43.2      |
| Running Reverse KL  | 11.9      |
| Running Update Time | 64        |
-----------------------------------
-2024-05-12 21:41:10.501883 ʱ--
| Itration            | 65        |
| Loss                | 88.8      |
| Real Det Return     | -4.28e+03 |
| Real Sto Return     | -3.41e+03 |
| Running Env Steps   | 325000    |
| Running Forward KL  | 43.2      |
| Running Reverse KL  | 12.4      |
| Running Update Time | 65        |
-----------------------------------
-2024-05-12 21:43:40.460812 ʱ--
| Itration            | 66        |
| Loss                | 55.2      |
| Real Det Return     | -4.4e+03  |
| Real Sto Return     | -3.66e+03 |
| Running Env Steps   | 330000    |
| Running Forward KL  | 43.8      |
| Running Reverse KL  | 12.1      |
| Running Update Time | 66        |
-----------------------------------
-2024-05-12 21:46:05.436268 ʱ--
| Itration            | 67        |
| Loss                | 16.8      |
| Real Det Return     | -4.11e+03 |
| Real Sto Return     | -3.39e+03 |
| Running Env Steps   | 335000    |
| Running Forward KL  | 43.4      |
| Running Reverse KL  | 12.1      |
| Running Update Time | 67        |
-----------------------------------
-2024-05-12 21:48:22.450246 ʱ--
| Itration            | 68        |
| Loss                | 82        |
| Real Det Return     | -4.23e+03 |
| Real Sto Return     | -3.47e+03 |
| Running Env Steps   | 340000    |
| Running Forward KL  | 43.4      |
| Running Reverse KL  | 12.6      |
| Running Update Time | 68        |
-----------------------------------
-2024-05-12 21:50:43.664844 ʱ--
| Itration            | 69        |
| Loss                | 94        |
| Real Det Return     | -4.07e+03 |
| Real Sto Return     | -3.37e+03 |
| Running Env Steps   | 345000    |
| Running Forward KL  | 43.1      |
| Running Reverse KL  | 11.9      |
| Running Update Time | 69        |
-----------------------------------
-2024-05-12 21:53:12.274664 ʱ--
| Itration            | 70        |
| Loss                | 12.6      |
| Real Det Return     | -3.32e+03 |
| Real Sto Return     | -2.94e+03 |
| Running Env Steps   | 350000    |
| Running Forward KL  | 41.6      |
| Running Reverse KL  | 10.7      |
| Running Update Time | 70        |
-----------------------------------
-2024-05-12 21:55:36.593440 ʱ--
| Itration            | 71        |
| Loss                | 67.4      |
| Real Det Return     | -4.36e+03 |
| Real Sto Return     | -3.47e+03 |
| Running Env Steps   | 355000    |
| Running Forward KL  | 43.2      |
| Running Reverse KL  | 12.1      |
| Running Update Time | 71        |
-----------------------------------
-2024-05-12 21:57:58.756096 ʱ--
| Itration            | 72        |
| Loss                | 22.6      |
| Real Det Return     | -4.11e+03 |
| Real Sto Return     | -3.44e+03 |
| Running Env Steps   | 360000    |
| Running Forward KL  | 42.7      |
| Running Reverse KL  | 12.2      |
| Running Update Time | 72        |
-----------------------------------
-2024-05-12 22:00:26.444186 ʱ--
| Itration            | 73        |
| Loss                | -2.61     |
| Real Det Return     | -2.52e+03 |
| Real Sto Return     | -2.3e+03  |
| Running Env Steps   | 365000    |
| Running Forward KL  | 40.7      |
| Running Reverse KL  | 10.4      |
| Running Update Time | 73        |
-----------------------------------
-2024-05-12 22:02:45.313855 ʱ--
| Itration            | 74        |
| Loss                | -11.3     |
| Real Det Return     | -3.94e+03 |
| Real Sto Return     | -3.35e+03 |
| Running Env Steps   | 370000    |
| Running Forward KL  | 42.5      |
| Running Reverse KL  | 11.3      |
| Running Update Time | 74        |
-----------------------------------
-2024-05-12 22:05:10.104023 ʱ--
| Itration            | 75        |
| Loss                | 40        |
| Real Det Return     | -3.9e+03  |
| Real Sto Return     | -3.28e+03 |
| Running Env Steps   | 375000    |
| Running Forward KL  | 42.8      |
| Running Reverse KL  | 12        |
| Running Update Time | 75        |
-----------------------------------
-2024-05-12 22:07:28.106024 ʱ--
| Itration            | 76        |
| Loss                | 71.6      |
| Real Det Return     | -4.25e+03 |
| Real Sto Return     | -3.44e+03 |
| Running Env Steps   | 380000    |
| Running Forward KL  | 43        |
| Running Reverse KL  | 11.7      |
| Running Update Time | 76        |
-----------------------------------
-2024-05-12 22:09:45.234278 ʱ--
| Itration            | 77        |
| Loss                | 59.3      |
| Real Det Return     | -4.23e+03 |
| Real Sto Return     | -3.54e+03 |
| Running Env Steps   | 385000    |
| Running Forward KL  | 43.2      |
| Running Reverse KL  | 12        |
| Running Update Time | 77        |
-----------------------------------
-2024-05-12 22:12:01.629851 ʱ--
| Itration            | 78        |
| Loss                | 75.9      |
| Real Det Return     | -4.48e+03 |
| Real Sto Return     | -3.53e+03 |
| Running Env Steps   | 390000    |
| Running Forward KL  | 43.3      |
| Running Reverse KL  | 11.9      |
| Running Update Time | 78        |
-----------------------------------
-2024-05-12 22:14:20.615724 ʱ--
| Itration            | 79        |
| Loss                | 47        |
| Real Det Return     | -4.3e+03  |
| Real Sto Return     | -3.58e+03 |
| Running Env Steps   | 395000    |
| Running Forward KL  | 43.6      |
| Running Reverse KL  | 11.3      |
| Running Update Time | 79        |
-----------------------------------
-2024-05-12 22:16:40.205576 ʱ--
| Itration            | 80        |
| Loss                | 25.6      |
| Real Det Return     | -4.34e+03 |
| Real Sto Return     | -3.48e+03 |
| Running Env Steps   | 400000    |
| Running Forward KL  | 43.4      |
| Running Reverse KL  | 11.7      |
| Running Update Time | 80        |
-----------------------------------
-2024-05-12 22:18:59.185961 ʱ--
| Itration            | 81        |
| Loss                | 11.9      |
| Real Det Return     | -4.41e+03 |
| Real Sto Return     | -3.42e+03 |
| Running Env Steps   | 405000    |
| Running Forward KL  | 42.5      |
| Running Reverse KL  | 11.3      |
| Running Update Time | 81        |
-----------------------------------
-2024-05-12 22:21:18.608286 ʱ--
| Itration            | 82        |
| Loss                | 30.3      |
| Real Det Return     | -4.31e+03 |
| Real Sto Return     | -3.47e+03 |
| Running Env Steps   | 410000    |
| Running Forward KL  | 43        |
| Running Reverse KL  | 11.4      |
| Running Update Time | 82        |
-----------------------------------
-2024-05-12 22:23:37.142941 ʱ--
| Itration            | 83        |
| Loss                | 20.8      |
| Real Det Return     | -4.26e+03 |
| Real Sto Return     | -3.52e+03 |
| Running Env Steps   | 415000    |
| Running Forward KL  | 42.7      |
| Running Reverse KL  | 11.6      |
| Running Update Time | 83        |
-----------------------------------
-2024-05-12 22:25:56.102085 ʱ--
| Itration            | 84        |
| Loss                | 42.5      |
| Real Det Return     | -4.38e+03 |
| Real Sto Return     | -3.51e+03 |
| Running Env Steps   | 420000    |
| Running Forward KL  | 43.2      |
| Running Reverse KL  | 12        |
| Running Update Time | 84        |
-----------------------------------
-2024-05-12 22:28:14.808746 ʱ--
| Itration            | 85        |
| Loss                | -2.9      |
| Real Det Return     | -4.38e+03 |
| Real Sto Return     | -3.43e+03 |
| Running Env Steps   | 425000    |
| Running Forward KL  | 42.9      |
| Running Reverse KL  | 11.4      |
| Running Update Time | 85        |
-----------------------------------
-2024-05-12 22:30:33.966857 ʱ--
| Itration            | 86        |
| Loss                | 25.4      |
| Real Det Return     | -4.18e+03 |
| Real Sto Return     | -3.36e+03 |
| Running Env Steps   | 430000    |
| Running Forward KL  | 42.6      |
| Running Reverse KL  | 10.9      |
| Running Update Time | 86        |
-----------------------------------
-2024-05-12 22:32:52.677211 ʱ--
| Itration            | 87        |
| Loss                | 0.224     |
| Real Det Return     | -4.16e+03 |
| Real Sto Return     | -3.27e+03 |
| Running Env Steps   | 435000    |
| Running Forward KL  | 42.7      |
| Running Reverse KL  | 10.6      |
| Running Update Time | 87        |
-----------------------------------
-2024-05-12 22:35:11.946080 ʱ--
| Itration            | 88        |
| Loss                | 51.9      |
| Real Det Return     | -4.58e+03 |
| Real Sto Return     | -3.55e+03 |
| Running Env Steps   | 440000    |
| Running Forward KL  | 43.3      |
| Running Reverse KL  | 11.3      |
| Running Update Time | 88        |
-----------------------------------
-2024-05-12 22:37:31.087323 ʱ--
| Itration            | 89        |
| Loss                | 62.9      |
| Real Det Return     | -4.49e+03 |
| Real Sto Return     | -3.58e+03 |
| Running Env Steps   | 445000    |
| Running Forward KL  | 42.1      |
| Running Reverse KL  | 11.1      |
| Running Update Time | 89        |
-----------------------------------
-2024-05-12 22:39:51.338902 ʱ--
| Itration            | 90        |
| Loss                | 32.1      |
| Real Det Return     | -4.06e+03 |
| Real Sto Return     | -3.22e+03 |
| Running Env Steps   | 450000    |
| Running Forward KL  | 42.7      |
| Running Reverse KL  | 11.3      |
| Running Update Time | 90        |
-----------------------------------
-2024-05-12 22:42:10.630498 ʱ--
| Itration            | 91        |
| Loss                | 12.5      |
| Real Det Return     | -3.77e+03 |
| Real Sto Return     | -3.11e+03 |
| Running Env Steps   | 455000    |
| Running Forward KL  | 41.9      |
| Running Reverse KL  | 10.5      |
| Running Update Time | 91        |
-----------------------------------
-2024-05-12 22:44:29.958857 ʱ--
| Itration            | 92        |
| Loss                | 39.1      |
| Real Det Return     | -4.09e+03 |
| Real Sto Return     | -3.31e+03 |
| Running Env Steps   | 460000    |
| Running Forward KL  | 42.3      |
| Running Reverse KL  | 11.1      |
| Running Update Time | 92        |
-----------------------------------
-2024-05-12 22:46:48.629244 ʱ--
| Itration            | 93        |
| Loss                | 38.8      |
| Real Det Return     | -4.62e+03 |
| Real Sto Return     | -3.32e+03 |
| Running Env Steps   | 465000    |
| Running Forward KL  | 41.8      |
| Running Reverse KL  | 10.7      |
| Running Update Time | 93        |
-----------------------------------
-2024-05-12 22:49:08.461778 ʱ--
| Itration            | 94        |
| Loss                | 19.6      |
| Real Det Return     | -4.56e+03 |
| Real Sto Return     | -3.27e+03 |
| Running Env Steps   | 470000    |
| Running Forward KL  | 42.9      |
| Running Reverse KL  | 10.9      |
| Running Update Time | 94        |
-----------------------------------
-2024-05-12 22:51:27.563819 ʱ--
| Itration            | 95        |
| Loss                | 18.1      |
| Real Det Return     | -3.57e+03 |
| Real Sto Return     | -3.14e+03 |
| Running Env Steps   | 475000    |
| Running Forward KL  | 41.8      |
| Running Reverse KL  | 10.2      |
| Running Update Time | 95        |
-----------------------------------
-2024-05-12 22:53:47.736946 ʱ--
| Itration            | 96        |
| Loss                | 33.7      |
| Real Det Return     | -4.18e+03 |
| Real Sto Return     | -3.4e+03  |
| Running Env Steps   | 480000    |
| Running Forward KL  | 42.4      |
| Running Reverse KL  | 11.1      |
| Running Update Time | 96        |
-----------------------------------
-2024-05-12 22:56:07.594790 ʱ--
| Itration            | 97        |
| Loss                | 51        |
| Real Det Return     | -3.89e+03 |
| Real Sto Return     | -3.29e+03 |
| Running Env Steps   | 485000    |
| Running Forward KL  | 41.9      |
| Running Reverse KL  | 10.4      |
| Running Update Time | 97        |
-----------------------------------
-2024-05-12 22:58:27.590971 ʱ--
| Itration            | 98        |
| Loss                | 66.1      |
| Real Det Return     | -4.13e+03 |
| Real Sto Return     | -3.23e+03 |
| Running Env Steps   | 490000    |
| Running Forward KL  | 42.8      |
| Running Reverse KL  | 10.6      |
| Running Update Time | 98        |
-----------------------------------
-2024-05-12 23:00:47.057217 ʱ--
| Itration            | 99        |
| Loss                | -14.3     |
| Real Det Return     | -4.13e+03 |
| Real Sto Return     | -3.16e+03 |
| Running Env Steps   | 495000    |
| Running Forward KL  | 42.6      |
| Running Reverse KL  | 10.4      |
| Running Update Time | 99        |
-----------------------------------
-2024-05-12 23:03:06.013495 ʱ--
| Itration            | 100       |
| Loss                | 42.1      |
| Real Det Return     | -4.32e+03 |
| Real Sto Return     | -3.18e+03 |
| Running Env Steps   | 500000    |
| Running Forward KL  | 42.5      |
| Running Reverse KL  | 10.4      |
| Running Update Time | 100       |
-----------------------------------
-2024-05-12 23:05:25.388119 ʱ--
| Itration            | 101       |
| Loss                | -12       |
| Real Det Return     | -4.33e+03 |
| Real Sto Return     | -3.14e+03 |
| Running Env Steps   | 505000    |
| Running Forward KL  | 42.3      |
| Running Reverse KL  | 10.4      |
| Running Update Time | 101       |
-----------------------------------
-2024-05-12 23:07:44.904636 ʱ--
| Itration            | 102       |
| Loss                | 103       |
| Real Det Return     | -4.41e+03 |
| Real Sto Return     | -3.18e+03 |
| Running Env Steps   | 510000    |
| Running Forward KL  | 42.3      |
| Running Reverse KL  | 10.8      |
| Running Update Time | 102       |
-----------------------------------
-2024-05-12 23:10:04.717697 ʱ--
| Itration            | 103       |
| Loss                | 70.2      |
| Real Det Return     | -4.15e+03 |
| Real Sto Return     | -3.26e+03 |
| Running Env Steps   | 515000    |
| Running Forward KL  | 42.6      |
| Running Reverse KL  | 10.8      |
| Running Update Time | 103       |
-----------------------------------
-2024-05-12 23:12:24.025318 ʱ--
| Itration            | 104       |
| Loss                | 43.3      |
| Real Det Return     | -3.74e+03 |
| Real Sto Return     | -3.26e+03 |
| Running Env Steps   | 520000    |
| Running Forward KL  | 42.4      |
| Running Reverse KL  | 10.7      |
| Running Update Time | 104       |
-----------------------------------
-2024-05-12 23:14:43.522283 ʱ--
| Itration            | 105       |
| Loss                | 43.5      |
| Real Det Return     | -3.76e+03 |
| Real Sto Return     | -3.26e+03 |
| Running Env Steps   | 525000    |
| Running Forward KL  | 42.7      |
| Running Reverse KL  | 10.5      |
| Running Update Time | 105       |
-----------------------------------
-2024-05-12 23:17:03.021523 ʱ--
| Itration            | 106       |
| Loss                | -6.55     |
| Real Det Return     | -4.16e+03 |
| Real Sto Return     | -2.98e+03 |
| Running Env Steps   | 530000    |
| Running Forward KL  | 41.1      |
| Running Reverse KL  | 9.91      |
| Running Update Time | 106       |
-----------------------------------
-2024-05-12 23:19:22.947437 ʱ--
| Itration            | 107       |
| Loss                | 48.3      |
| Real Det Return     | -4.04e+03 |
| Real Sto Return     | -3.04e+03 |
| Running Env Steps   | 535000    |
| Running Forward KL  | 41.7      |
| Running Reverse KL  | 9.87      |
| Running Update Time | 107       |
-----------------------------------
-2024-05-12 23:21:42.586963 ʱ--
| Itration            | 108       |
| Loss                | -35.3     |
| Real Det Return     | -3.88e+03 |
| Real Sto Return     | -2.82e+03 |
| Running Env Steps   | 540000    |
| Running Forward KL  | 41.2      |
| Running Reverse KL  | 9.46      |
| Running Update Time | 108       |
-----------------------------------
-2024-05-12 23:24:02.332095 ʱ--
| Itration            | 109       |
| Loss                | 9.42      |
| Real Det Return     | -4.5e+03  |
| Real Sto Return     | -3.14e+03 |
| Running Env Steps   | 545000    |
| Running Forward KL  | 42.5      |
| Running Reverse KL  | 10.2      |
| Running Update Time | 109       |
-----------------------------------
-2024-05-12 23:26:22.109010 ʱ--
| Itration            | 110       |
| Loss                | 28.1      |
| Real Det Return     | -3.92e+03 |
| Real Sto Return     | -3e+03    |
| Running Env Steps   | 550000    |
| Running Forward KL  | 41.1      |
| Running Reverse KL  | 9.52      |
| Running Update Time | 110       |
-----------------------------------
-2024-05-12 23:28:45.701497 ʱ--
| Itration            | 111       |
| Loss                | 27.6      |
| Real Det Return     | -3.8e+03  |
| Real Sto Return     | -3.09e+03 |
| Running Env Steps   | 555000    |
| Running Forward KL  | 41.5      |
| Running Reverse KL  | 9.98      |
| Running Update Time | 111       |
-----------------------------------
-2024-05-12 23:31:06.816856 ʱ--
| Itration            | 112       |
| Loss                | 56.1      |
| Real Det Return     | -3.79e+03 |
| Real Sto Return     | -2.77e+03 |
| Running Env Steps   | 560000    |
| Running Forward KL  | 41        |
| Running Reverse KL  | 9.53      |
| Running Update Time | 112       |
-----------------------------------
-2024-05-12 23:33:27.788224 ʱ--
| Itration            | 113       |
| Loss                | 30.1      |
| Real Det Return     | -3.74e+03 |
| Real Sto Return     | -2.95e+03 |
| Running Env Steps   | 565000    |
| Running Forward KL  | 41.4      |
| Running Reverse KL  | 9.48      |
| Running Update Time | 113       |
-----------------------------------
-2024-05-12 23:35:48.404087 ʱ--
| Itration            | 114       |
| Loss                | -7.43     |
| Real Det Return     | -4.04e+03 |
| Real Sto Return     | -2.9e+03  |
| Running Env Steps   | 570000    |
| Running Forward KL  | 40.9      |
| Running Reverse KL  | 9.71      |
| Running Update Time | 114       |
-----------------------------------
-2024-05-12 23:38:09.138041 ʱ--
| Itration            | 115       |
| Loss                | -12.5     |
| Real Det Return     | -3.82e+03 |
| Real Sto Return     | -2.71e+03 |
| Running Env Steps   | 575000    |
| Running Forward KL  | 40.1      |
| Running Reverse KL  | 9.12      |
| Running Update Time | 115       |
-----------------------------------
-2024-05-12 23:40:30.608754 ʱ--
| Itration            | 116       |
| Loss                | 42.6      |
| Real Det Return     | -4.71e+03 |
| Real Sto Return     | -3e+03    |
| Running Env Steps   | 580000    |
| Running Forward KL  | 41.2      |
| Running Reverse KL  | 9.13      |
| Running Update Time | 116       |
-----------------------------------
-2024-05-12 23:42:49.645490 ʱ--
| Itration            | 117       |
| Loss                | 32.8      |
| Real Det Return     | -3.67e+03 |
| Real Sto Return     | -2.71e+03 |
| Running Env Steps   | 585000    |
| Running Forward KL  | 40.3      |
| Running Reverse KL  | 9.35      |
| Running Update Time | 117       |
-----------------------------------
-2024-05-12 23:44:59.983902 ʱ--
| Itration            | 118       |
| Loss                | -33.3     |
| Real Det Return     | -4.14e+03 |
| Real Sto Return     | -2.52e+03 |
| Running Env Steps   | 590000    |
| Running Forward KL  | 40.7      |
| Running Reverse KL  | 8.89      |
| Running Update Time | 118       |
-----------------------------------
-2024-05-12 23:47:07.775693 ʱ--
| Itration            | 119       |
| Loss                | -35       |
| Real Det Return     | -4.61e+03 |
| Real Sto Return     | -2.65e+03 |
| Running Env Steps   | 595000    |
| Running Forward KL  | 40.8      |
| Running Reverse KL  | 8.98      |
| Running Update Time | 119       |
-----------------------------------
-2024-05-12 23:49:15.571875 ʱ--
| Itration            | 120       |
| Loss                | -26.4     |
| Real Det Return     | -3.58e+03 |
| Real Sto Return     | -2.66e+03 |
| Running Env Steps   | 600000    |
| Running Forward KL  | 40.9      |
| Running Reverse KL  | 8.83      |
| Running Update Time | 120       |
-----------------------------------
-2024-05-12 23:51:23.777265 ʱ--
| Itration            | 121       |
| Loss                | -16.7     |
| Real Det Return     | -4.1e+03  |
| Real Sto Return     | -2.51e+03 |
| Running Env Steps   | 605000    |
| Running Forward KL  | 39.9      |
| Running Reverse KL  | 8.47      |
| Running Update Time | 121       |
-----------------------------------
-2024-05-12 23:53:32.048568 ʱ--
| Itration            | 122       |
| Loss                | -20.3     |
| Real Det Return     | -3.49e+03 |
| Real Sto Return     | -2.69e+03 |
| Running Env Steps   | 610000    |
| Running Forward KL  | 40.8      |
| Running Reverse KL  | 8.85      |
| Running Update Time | 122       |
-----------------------------------
-2024-05-12 23:55:39.713623 ʱ--
| Itration            | 123       |
| Loss                | 9.68      |
| Real Det Return     | -3.97e+03 |
| Real Sto Return     | -2.66e+03 |
| Running Env Steps   | 615000    |
| Running Forward KL  | 40.7      |
| Running Reverse KL  | 8.82      |
| Running Update Time | 123       |
-----------------------------------
-2024-05-12 23:57:47.732097 ʱ--
| Itration            | 124       |
| Loss                | -18.1     |
| Real Det Return     | -4.39e+03 |
| Real Sto Return     | -2.53e+03 |
| Running Env Steps   | 620000    |
| Running Forward KL  | 41.2      |
| Running Reverse KL  | 9.04      |
| Running Update Time | 124       |
-----------------------------------
-2024-05-12 23:59:55.665569 ʱ--
| Itration            | 125       |
| Loss                | -29.4     |
| Real Det Return     | -4.46e+03 |
| Real Sto Return     | -2.84e+03 |
| Running Env Steps   | 625000    |
| Running Forward KL  | 41.1      |
| Running Reverse KL  | 8.64      |
| Running Update Time | 125       |
-----------------------------------
-2024-05-13 00:02:03.428161 ʱ--
| Itration            | 126       |
| Loss                | 19.3      |
| Real Det Return     | -4.48e+03 |
| Real Sto Return     | -2.97e+03 |
| Running Env Steps   | 630000    |
| Running Forward KL  | 40.9      |
| Running Reverse KL  | 8.72      |
| Running Update Time | 126       |
-----------------------------------
-2024-05-13 00:04:11.654643 ʱ--
| Itration            | 127       |
| Loss                | 55.1      |
| Real Det Return     | -3.64e+03 |
| Real Sto Return     | -2.65e+03 |
| Running Env Steps   | 635000    |
| Running Forward KL  | 40.5      |
| Running Reverse KL  | 8.77      |
| Running Update Time | 127       |
-----------------------------------
-2024-05-13 00:06:20.593994 ʱ--
| Itration            | 128       |
| Loss                | 6.65      |
| Real Det Return     | -4.21e+03 |
| Real Sto Return     | -2.58e+03 |
| Running Env Steps   | 640000    |
| Running Forward KL  | 40.7      |
| Running Reverse KL  | 8.53      |
| Running Update Time | 128       |
-----------------------------------
-2024-05-13 00:08:28.766817 ʱ--
| Itration            | 129       |
| Loss                | -24.3     |
| Real Det Return     | -3.11e+03 |
| Real Sto Return     | -2.46e+03 |
| Running Env Steps   | 645000    |
| Running Forward KL  | 39.9      |
| Running Reverse KL  | 8.45      |
| Running Update Time | 129       |
-----------------------------------
-2024-05-13 00:10:37.116429 ʱ--
| Itration            | 130       |
| Loss                | -7.73     |
| Real Det Return     | -4.89e+03 |
| Real Sto Return     | -2.58e+03 |
| Running Env Steps   | 650000    |
| Running Forward KL  | 39.3      |
| Running Reverse KL  | 8.34      |
| Running Update Time | 130       |
-----------------------------------
-2024-05-13 00:12:45.951864 ʱ--
| Itration            | 131       |
| Loss                | 33.4      |
| Real Det Return     | -4.35e+03 |
| Real Sto Return     | -2.76e+03 |
| Running Env Steps   | 655000    |
| Running Forward KL  | 40.5      |
| Running Reverse KL  | 8.4       |
| Running Update Time | 131       |
-----------------------------------
-2024-05-13 00:14:54.859770 ʱ--
| Itration            | 132       |
| Loss                | 15.9      |
| Real Det Return     | -4.76e+03 |
| Real Sto Return     | -2.56e+03 |
| Running Env Steps   | 660000    |
| Running Forward KL  | 40.3      |
| Running Reverse KL  | 8.26      |
| Running Update Time | 132       |
-----------------------------------
-2024-05-13 00:17:05.872967 ʱ--
| Itration            | 133       |
| Loss                | -25.7     |
| Real Det Return     | -4.48e+03 |
| Real Sto Return     | -2.75e+03 |
| Running Env Steps   | 665000    |
| Running Forward KL  | 39.9      |
| Running Reverse KL  | 8.2       |
| Running Update Time | 133       |
-----------------------------------
-2024-05-13 00:19:14.923855 ʱ--
| Itration            | 134       |
| Loss                | -10.2     |
| Real Det Return     | -4.37e+03 |
| Real Sto Return     | -2.53e+03 |
| Running Env Steps   | 670000    |
| Running Forward KL  | 40        |
| Running Reverse KL  | 7.72      |
| Running Update Time | 134       |
-----------------------------------
-2024-05-13 00:21:23.733245 ʱ--
| Itration            | 135       |
| Loss                | -8.77     |
| Real Det Return     | -5.07e+03 |
| Real Sto Return     | -2.62e+03 |
| Running Env Steps   | 675000    |
| Running Forward KL  | 40.4      |
| Running Reverse KL  | 8.16      |
| Running Update Time | 135       |
-----------------------------------
-2024-05-13 00:23:32.843406 ʱ--
| Itration            | 136       |
| Loss                | -37.7     |
| Real Det Return     | -4.11e+03 |
| Real Sto Return     | -2.54e+03 |
| Running Env Steps   | 680000    |
| Running Forward KL  | 40.2      |
| Running Reverse KL  | 8.27      |
| Running Update Time | 136       |
-----------------------------------
-2024-05-13 00:25:42.239276 ʱ--
| Itration            | 137       |
| Loss                | -7.43     |
| Real Det Return     | -3.3e+03  |
| Real Sto Return     | -2.42e+03 |
| Running Env Steps   | 685000    |
| Running Forward KL  | 40.5      |
| Running Reverse KL  | 8.36      |
| Running Update Time | 137       |
-----------------------------------
-2024-05-13 00:27:51.345793 ʱ--
| Itration            | 138       |
| Loss                | 20.5      |
| Real Det Return     | -4.35e+03 |
| Real Sto Return     | -2.57e+03 |
| Running Env Steps   | 690000    |
| Running Forward KL  | 39.5      |
| Running Reverse KL  | 8.38      |
| Running Update Time | 138       |
-----------------------------------
-2024-05-13 00:30:00.621889 ʱ--
| Itration            | 139       |
| Loss                | -3.49     |
| Real Det Return     | -5e+03    |
| Real Sto Return     | -2.23e+03 |
| Running Env Steps   | 695000    |
| Running Forward KL  | 39.5      |
| Running Reverse KL  | 7.62      |
| Running Update Time | 139       |
-----------------------------------
-2024-05-13 00:32:10.272232 ʱ--
| Itration            | 140       |
| Loss                | -25.8     |
| Real Det Return     | -3.5e+03  |
| Real Sto Return     | -2.54e+03 |
| Running Env Steps   | 700000    |
| Running Forward KL  | 40.6      |
| Running Reverse KL  | 7.65      |
| Running Update Time | 140       |
-----------------------------------
-2024-05-13 00:34:20.068406 ʱ--
| Itration            | 141       |
| Loss                | -44       |
| Real Det Return     | -3.15e+03 |
| Real Sto Return     | -2.23e+03 |
| Running Env Steps   | 705000    |
| Running Forward KL  | 39.6      |
| Running Reverse KL  | 7.48      |
| Running Update Time | 141       |
-----------------------------------
-2024-05-13 00:36:29.843789 ʱ--
| Itration            | 142       |
| Loss                | -34.4     |
| Real Det Return     | -4.58e+03 |
| Real Sto Return     | -2.28e+03 |
| Running Env Steps   | 710000    |
| Running Forward KL  | 38.8      |
| Running Reverse KL  | 7.32      |
| Running Update Time | 142       |
-----------------------------------
-2024-05-13 00:38:39.710119 ʱ--
| Itration            | 143       |
| Loss                | -105      |
| Real Det Return     | -3.14e+03 |
| Real Sto Return     | -2.12e+03 |
| Running Env Steps   | 715000    |
| Running Forward KL  | 39.2      |
| Running Reverse KL  | 7.03      |
| Running Update Time | 143       |
-----------------------------------
-2024-05-13 00:40:49.542323 ʱ--
| Itration            | 144       |
| Loss                | -71.3     |
| Real Det Return     | -3.35e+03 |
| Real Sto Return     | -2.26e+03 |
| Running Env Steps   | 720000    |
| Running Forward KL  | 39.7      |
| Running Reverse KL  | 7.43      |
| Running Update Time | 144       |
-----------------------------------
-2024-05-13 00:42:59.578671 ʱ--
| Itration            | 145       |
| Loss                | -41.5     |
| Real Det Return     | -3.35e+03 |
| Real Sto Return     | -2.28e+03 |
| Running Env Steps   | 725000    |
| Running Forward KL  | 39.5      |
| Running Reverse KL  | 7.11      |
| Running Update Time | 145       |
-----------------------------------
-2024-05-13 00:45:09.871919 ʱ--
| Itration            | 146       |
| Loss                | -36.6     |
| Real Det Return     | -2.98e+03 |
| Real Sto Return     | -2.05e+03 |
| Running Env Steps   | 730000    |
| Running Forward KL  | 39.5      |
| Running Reverse KL  | 7.54      |
| Running Update Time | 146       |
-----------------------------------
-2024-05-13 00:47:20.273452 ʱ--
| Itration            | 147       |
| Loss                | -105      |
| Real Det Return     | -4.35e+03 |
| Real Sto Return     | -2.21e+03 |
| Running Env Steps   | 735000    |
| Running Forward KL  | 39.1      |
| Running Reverse KL  | 7.09      |
| Running Update Time | 147       |
-----------------------------------
-2024-05-13 00:49:30.433423 ʱ--
| Itration            | 148       |
| Loss                | -9.11     |
| Real Det Return     | -3.35e+03 |
| Real Sto Return     | -2.22e+03 |
| Running Env Steps   | 740000    |
| Running Forward KL  | 39.2      |
| Running Reverse KL  | 7.1       |
| Running Update Time | 148       |
-----------------------------------
-2024-05-13 00:51:40.770125 ʱ--
| Itration            | 149       |
| Loss                | -61.8     |
| Real Det Return     | -3.12e+03 |
| Real Sto Return     | -1.91e+03 |
| Running Env Steps   | 745000    |
| Running Forward KL  | 39.1      |
| Running Reverse KL  | 7.14      |
| Running Update Time | 149       |
-----------------------------------
-2024-05-13 00:53:51.542744 ʱ--
| Itration            | 150       |
| Loss                | -43.1     |
| Real Det Return     | -3.41e+03 |
| Real Sto Return     | -1.97e+03 |
| Running Env Steps   | 750000    |
| Running Forward KL  | 39        |
| Running Reverse KL  | 6.98      |
| Running Update Time | 150       |
-----------------------------------
-2024-05-13 00:56:02.359159 ʱ--
| Itration            | 151       |
| Loss                | -44       |
| Real Det Return     | -3.91e+03 |
| Real Sto Return     | -2.06e+03 |
| Running Env Steps   | 755000    |
| Running Forward KL  | 39        |
| Running Reverse KL  | 6.92      |
| Running Update Time | 151       |
-----------------------------------
-2024-05-13 00:58:13.528377 ʱ--
| Itration            | 152       |
| Loss                | -34       |
| Real Det Return     | -3.33e+03 |
| Real Sto Return     | -2.12e+03 |
| Running Env Steps   | 760000    |
| Running Forward KL  | 38.2      |
| Running Reverse KL  | 6.75      |
| Running Update Time | 152       |
-----------------------------------
-2024-05-13 01:00:24.202842 ʱ--
| Itration            | 153       |
| Loss                | -57.8     |
| Real Det Return     | -3.06e+03 |
| Real Sto Return     | -1.79e+03 |
| Running Env Steps   | 765000    |
| Running Forward KL  | 38.4      |
| Running Reverse KL  | 6.74      |
| Running Update Time | 153       |
-----------------------------------
-2024-05-13 01:02:35.414166 ʱ--
| Itration            | 154       |
| Loss                | -51.6     |
| Real Det Return     | -3.31e+03 |
| Real Sto Return     | -1.87e+03 |
| Running Env Steps   | 770000    |
| Running Forward KL  | 38.5      |
| Running Reverse KL  | 6.4       |
| Running Update Time | 154       |
-----------------------------------
-2024-05-13 01:04:46.335646 ʱ--
| Itration            | 155       |
| Loss                | -70       |
| Real Det Return     | -3.32e+03 |
| Real Sto Return     | -1.96e+03 |
| Running Env Steps   | 775000    |
| Running Forward KL  | 38.9      |
| Running Reverse KL  | 6.41      |
| Running Update Time | 155       |
-----------------------------------
-2024-05-13 01:06:57.545522 ʱ--
| Itration            | 156       |
| Loss                | -23.5     |
| Real Det Return     | -2.91e+03 |
| Real Sto Return     | -1.88e+03 |
| Running Env Steps   | 780000    |
| Running Forward KL  | 37.5      |
| Running Reverse KL  | 6.91      |
| Running Update Time | 156       |
-----------------------------------
-2024-05-13 01:09:08.588384 ʱ--
| Itration            | 157       |
| Loss                | -76.3     |
| Real Det Return     | -3.21e+03 |
| Real Sto Return     | -1.75e+03 |
| Running Env Steps   | 785000    |
| Running Forward KL  | 38.5      |
| Running Reverse KL  | 6.47      |
| Running Update Time | 157       |
-----------------------------------
-2024-05-13 01:11:20.178775 ʱ--
| Itration            | 158       |
| Loss                | -56.8     |
| Real Det Return     | -3.22e+03 |
| Real Sto Return     | -1.87e+03 |
| Running Env Steps   | 790000    |
| Running Forward KL  | 38.5      |
| Running Reverse KL  | 6.81      |
| Running Update Time | 158       |
-----------------------------------
-2024-05-13 01:13:31.693480 ʱ--
| Itration            | 159       |
| Loss                | -64.7     |
| Real Det Return     | -2.98e+03 |
| Real Sto Return     | -1.63e+03 |
| Running Env Steps   | 795000    |
| Running Forward KL  | 38.9      |
| Running Reverse KL  | 6.27      |
| Running Update Time | 159       |
-----------------------------------
-2024-05-13 01:15:43.608866 ʱ--
| Itration            | 160       |
| Loss                | -88.2     |
| Real Det Return     | -3e+03    |
| Real Sto Return     | -1.83e+03 |
| Running Env Steps   | 800000    |
| Running Forward KL  | 38.4      |
| Running Reverse KL  | 6.2       |
| Running Update Time | 160       |
-----------------------------------
-2024-05-13 01:17:56.592609 ʱ--
| Itration            | 161       |
| Loss                | -75.7     |
| Real Det Return     | -2.85e+03 |
| Real Sto Return     | -1.69e+03 |
| Running Env Steps   | 805000    |
| Running Forward KL  | 37.9      |
| Running Reverse KL  | 6.05      |
| Running Update Time | 161       |
-----------------------------------
-2024-05-13 01:20:09.467016 ʱ--
| Itration            | 162       |
| Loss                | -41.3     |
| Real Det Return     | -2.51e+03 |
| Real Sto Return     | -1.57e+03 |
| Running Env Steps   | 810000    |
| Running Forward KL  | 37.9      |
| Running Reverse KL  | 5.76      |
| Running Update Time | 162       |
-----------------------------------
-2024-05-13 01:22:22.145588 ʱ--
| Itration            | 163       |
| Loss                | -43.5     |
| Real Det Return     | -2.81e+03 |
| Real Sto Return     | -1.57e+03 |
| Running Env Steps   | 815000    |
| Running Forward KL  | 38.6      |
| Running Reverse KL  | 6.49      |
| Running Update Time | 163       |
-----------------------------------
-2024-05-13 01:24:35.183095 ʱ--
| Itration            | 164       |
| Loss                | -57.1     |
| Real Det Return     | -2.67e+03 |
| Real Sto Return     | -1.59e+03 |
| Running Env Steps   | 820000    |
| Running Forward KL  | 37.3      |
| Running Reverse KL  | 5.85      |
| Running Update Time | 164       |
-----------------------------------
-2024-05-13 01:26:47.148766 ʱ--
| Itration            | 165       |
| Loss                | -122      |
| Real Det Return     | -2.97e+03 |
| Real Sto Return     | -1.48e+03 |
| Running Env Steps   | 825000    |
| Running Forward KL  | 37.7      |
| Running Reverse KL  | 5.73      |
| Running Update Time | 165       |
-----------------------------------
-2024-05-13 01:28:59.450368 ʱ--
| Itration            | 166       |
| Loss                | -75.5     |
| Real Det Return     | -2.83e+03 |
| Real Sto Return     | -1.64e+03 |
| Running Env Steps   | 830000    |
| Running Forward KL  | 38.2      |
| Running Reverse KL  | 6.18      |
| Running Update Time | 166       |
-----------------------------------
-2024-05-13 01:31:12.014695 ʱ--
| Itration            | 167       |
| Loss                | -63.5     |
| Real Det Return     | -2.87e+03 |
| Real Sto Return     | -1.69e+03 |
| Running Env Steps   | 835000    |
| Running Forward KL  | 37.1      |
| Running Reverse KL  | 5.85      |
| Running Update Time | 167       |
-----------------------------------
-2024-05-13 01:33:24.321775 ʱ--
| Itration            | 168       |
| Loss                | -82.2     |
| Real Det Return     | -2.46e+03 |
| Real Sto Return     | -1.33e+03 |
| Running Env Steps   | 840000    |
| Running Forward KL  | 37.4      |
| Running Reverse KL  | 5.91      |
| Running Update Time | 168       |
-----------------------------------
-2024-05-13 01:35:37.547824 ʱ--
| Itration            | 169       |
| Loss                | -58.1     |
| Real Det Return     | -3.15e+03 |
| Real Sto Return     | -1.69e+03 |
| Running Env Steps   | 845000    |
| Running Forward KL  | 37.5      |
| Running Reverse KL  | 6.01      |
| Running Update Time | 169       |
-----------------------------------
-2024-05-13 01:37:50.238638 ʱ--
| Itration            | 170       |
| Loss                | -52.7     |
| Real Det Return     | -2.46e+03 |
| Real Sto Return     | -1.31e+03 |
| Running Env Steps   | 850000    |
| Running Forward KL  | 36.9      |
| Running Reverse KL  | 5.64      |
| Running Update Time | 170       |
-----------------------------------
-2024-05-13 01:40:03.491455 ʱ--
| Itration            | 171       |
| Loss                | -97.6     |
| Real Det Return     | -2.86e+03 |
| Real Sto Return     | -1.65e+03 |
| Running Env Steps   | 855000    |
| Running Forward KL  | 37.7      |
| Running Reverse KL  | 6.05      |
| Running Update Time | 171       |
-----------------------------------
-2024-05-13 01:42:16.160960 ʱ--
| Itration            | 172       |
| Loss                | -59.1     |
| Real Det Return     | -2.92e+03 |
| Real Sto Return     | -1.46e+03 |
| Running Env Steps   | 860000    |
| Running Forward KL  | 38.8      |
| Running Reverse KL  | 6.02      |
| Running Update Time | 172       |
-----------------------------------
-2024-05-13 01:44:29.942659 ʱ-
| Itration            | 173      |
| Loss                | -80.3    |
| Real Det Return     | -2.8e+03 |
| Real Sto Return     | -1.6e+03 |
| Running Env Steps   | 865000   |
| Running Forward KL  | 37.8     |
| Running Reverse KL  | 5.68     |
| Running Update Time | 173      |
----------------------------------
-2024-05-13 01:46:51.951078 ʱ--
| Itration            | 174       |
| Loss                | -91.3     |
| Real Det Return     | -2.64e+03 |
| Real Sto Return     | -1.38e+03 |
| Running Env Steps   | 870000    |
| Running Forward KL  | 37.2      |
| Running Reverse KL  | 5.51      |
| Running Update Time | 174       |
-----------------------------------
-2024-05-13 01:49:17.947082 ʱ--
| Itration            | 175       |
| Loss                | -62.4     |
| Real Det Return     | -2.76e+03 |
| Real Sto Return     | -1.26e+03 |
| Running Env Steps   | 875000    |
| Running Forward KL  | 36.3      |
| Running Reverse KL  | 5.57      |
| Running Update Time | 175       |
-----------------------------------
-2024-05-13 01:51:45.658796 ʱ--
| Itration            | 176       |
| Loss                | -63.4     |
| Real Det Return     | -2.36e+03 |
| Real Sto Return     | -1.2e+03  |
| Running Env Steps   | 880000    |
| Running Forward KL  | 37.2      |
| Running Reverse KL  | 5.6       |
| Running Update Time | 176       |
-----------------------------------
-2024-05-13 01:54:10.331931 ʱ--
| Itration            | 177       |
| Loss                | -119      |
| Real Det Return     | -2.48e+03 |
| Real Sto Return     | -1.19e+03 |
| Running Env Steps   | 885000    |
| Running Forward KL  | 36.8      |
| Running Reverse KL  | 5.37      |
| Running Update Time | 177       |
-----------------------------------
-2024-05-13 01:56:35.291462 ʱ--
| Itration            | 178       |
| Loss                | -65.7     |
| Real Det Return     | -2.49e+03 |
| Real Sto Return     | -1.2e+03  |
| Running Env Steps   | 890000    |
| Running Forward KL  | 37.5      |
| Running Reverse KL  | 5.31      |
| Running Update Time | 178       |
-----------------------------------
-2024-05-13 01:59:00.667726 ʱ--
| Itration            | 179       |
| Loss                | -92.4     |
| Real Det Return     | -2.35e+03 |
| Real Sto Return     | -1.08e+03 |
| Running Env Steps   | 895000    |
| Running Forward KL  | 37.1      |
| Running Reverse KL  | 5.24      |
| Running Update Time | 179       |
-----------------------------------
-2024-05-13 02:01:26.058231 ʱ-
| Itration            | 180      |
| Loss                | -79.4    |
| Real Det Return     | -2.4e+03 |
| Real Sto Return     | -1.2e+03 |
| Running Env Steps   | 900000   |
| Running Forward KL  | 37.4     |
| Running Reverse KL  | 5.52     |
| Running Update Time | 180      |
----------------------------------
-2024-05-13 02:03:51.376355 ʱ--
| Itration            | 181       |
| Loss                | -75.6     |
| Real Det Return     | -2.54e+03 |
| Real Sto Return     | -952      |
| Running Env Steps   | 905000    |
| Running Forward KL  | 36.9      |
| Running Reverse KL  | 5.32      |
| Running Update Time | 181       |
-----------------------------------
-2024-05-13 02:06:17.303020 ʱ--
| Itration            | 182       |
| Loss                | -57.7     |
| Real Det Return     | -2.21e+03 |
| Real Sto Return     | -1.06e+03 |
| Running Env Steps   | 910000    |
| Running Forward KL  | 37.1      |
| Running Reverse KL  | 5.29      |
| Running Update Time | 182       |
-----------------------------------
-2024-05-13 02:08:42.363714 ʱ--
| Itration            | 183       |
| Loss                | -73.8     |
| Real Det Return     | -2.03e+03 |
| Real Sto Return     | -834      |
| Running Env Steps   | 915000    |
| Running Forward KL  | 35.8      |
| Running Reverse KL  | 4.85      |
| Running Update Time | 183       |
-----------------------------------
-2024-05-13 02:11:07.068293 ʱ--
| Itration            | 184       |
| Loss                | -60.2     |
| Real Det Return     | -2.21e+03 |
| Real Sto Return     | -925      |
| Running Env Steps   | 920000    |
| Running Forward KL  | 36.5      |
| Running Reverse KL  | 5.27      |
| Running Update Time | 184       |
-----------------------------------
-2024-05-13 02:13:33.026661 ʱ--
| Itration            | 185       |
| Loss                | -69.9     |
| Real Det Return     | -2.25e+03 |
| Real Sto Return     | -713      |
| Running Env Steps   | 925000    |
| Running Forward KL  | 36.4      |
| Running Reverse KL  | 5.52      |
| Running Update Time | 185       |
-----------------------------------
-2024-05-13 02:15:58.031797 ʱ--
| Itration            | 186       |
| Loss                | -133      |
| Real Det Return     | -1.91e+03 |
| Real Sto Return     | -761      |
| Running Env Steps   | 930000    |
| Running Forward KL  | 35.3      |
| Running Reverse KL  | 4.81      |
| Running Update Time | 186       |
-----------------------------------
-2024-05-13 02:18:24.363733 ʱ--
| Itration            | 187       |
| Loss                | -99.1     |
| Real Det Return     | -2.19e+03 |
| Real Sto Return     | -885      |
| Running Env Steps   | 935000    |
| Running Forward KL  | 36.3      |
| Running Reverse KL  | 5.05      |
| Running Update Time | 187       |
-----------------------------------
-2024-05-13 02:20:50.114676 ʱ--
| Itration            | 188       |
| Loss                | -103      |
| Real Det Return     | -2.02e+03 |
| Real Sto Return     | -713      |
| Running Env Steps   | 940000    |
| Running Forward KL  | 35.4      |
| Running Reverse KL  | 4.68      |
| Running Update Time | 188       |
-----------------------------------
-2024-05-13 02:23:16.347960 ʱ-
| Itration            | 189      |
| Loss                | -98.2    |
| Real Det Return     | -2.4e+03 |
| Real Sto Return     | -770     |
| Running Env Steps   | 945000   |
| Running Forward KL  | 36.4     |
| Running Reverse KL  | 4.88     |
| Running Update Time | 189      |
----------------------------------
-2024-05-13 02:25:42.080459 ʱ--
| Itration            | 190       |
| Loss                | -85.9     |
| Real Det Return     | -2.12e+03 |
| Real Sto Return     | -777      |
| Running Env Steps   | 950000    |
| Running Forward KL  | 35.8      |
| Running Reverse KL  | 4.89      |
| Running Update Time | 190       |
-----------------------------------
-2024-05-13 02:28:07.773264 ʱ-
| Itration            | 191      |
| Loss                | -84.5    |
| Real Det Return     | -2.1e+03 |
| Real Sto Return     | -696     |
| Running Env Steps   | 955000   |
| Running Forward KL  | 36.7     |
| Running Reverse KL  | 5.17     |
| Running Update Time | 191      |
----------------------------------
-2024-05-13 02:30:34.109089 ʱ-
| Itration            | 192      |
| Loss                | -91.4    |
| Real Det Return     | -2e+03   |
| Real Sto Return     | -741     |
| Running Env Steps   | 960000   |
| Running Forward KL  | 35.7     |
| Running Reverse KL  | 4.96     |
| Running Update Time | 192      |
----------------------------------
-2024-05-13 02:33:00.326984 ʱ--
| Itration            | 193       |
| Loss                | -162      |
| Real Det Return     | -1.83e+03 |
| Real Sto Return     | -557      |
| Running Env Steps   | 965000    |
| Running Forward KL  | 35.9      |
| Running Reverse KL  | 4.58      |
| Running Update Time | 193       |
-----------------------------------
-2024-05-13 02:35:26.796186 ʱ--
| Itration            | 194       |
| Loss                | -118      |
| Real Det Return     | -1.97e+03 |
| Real Sto Return     | -761      |
| Running Env Steps   | 970000    |
| Running Forward KL  | 35.8      |
| Running Reverse KL  | 5.03      |
| Running Update Time | 194       |
-----------------------------------
-2024-05-13 02:37:53.501693 ʱ--
| Itration            | 195       |
| Loss                | -115      |
| Real Det Return     | -1.89e+03 |
| Real Sto Return     | -716      |
| Running Env Steps   | 975000    |
| Running Forward KL  | 36.5      |
| Running Reverse KL  | 4.82      |
| Running Update Time | 195       |
-----------------------------------
-2024-05-13 02:40:19.835325 ʱ-
| Itration            | 196      |
| Loss                | -69      |
| Real Det Return     | -1.8e+03 |
| Real Sto Return     | -634     |
| Running Env Steps   | 980000   |
| Running Forward KL  | 35       |
| Running Reverse KL  | 4.91     |
| Running Update Time | 196      |
----------------------------------
-2024-05-13 02:42:46.269772 ʱ--
| Itration            | 197       |
| Loss                | -131      |
| Real Det Return     | -1.72e+03 |
| Real Sto Return     | -559      |
| Running Env Steps   | 985000    |
| Running Forward KL  | 36        |
| Running Reverse KL  | 4.85      |
| Running Update Time | 197       |
-----------------------------------
-2024-05-13 02:45:12.686348 ʱ--
| Itration            | 198       |
| Loss                | -122      |
| Real Det Return     | -2.09e+03 |
| Real Sto Return     | -731      |
| Running Env Steps   | 990000    |
| Running Forward KL  | 35.6      |
| Running Reverse KL  | 4.61      |
| Running Update Time | 198       |
-----------------------------------
-2024-05-13 02:47:38.752592 ʱ--
| Itration            | 199       |
| Loss                | -117      |
| Real Det Return     | -1.88e+03 |
| Real Sto Return     | -658      |
| Running Env Steps   | 995000    |
| Running Forward KL  | 36.1      |
| Running Reverse KL  | 4.96      |
| Running Update Time | 199       |
-----------------------------------
-2024-05-13 02:50:06.248839 ʱ-
| Itration            | 200      |
| Loss                | -87.3    |
| Real Det Return     | -2.1e+03 |
| Real Sto Return     | -640     |
| Running Env Steps   | 1000000  |
| Running Forward KL  | 34.8     |
| Running Reverse KL  | 4.51     |
| Running Update Time | 200      |
----------------------------------
-2024-05-13 02:52:33.555193 ʱ--
| Itration            | 201       |
| Loss                | -114      |
| Real Det Return     | -1.98e+03 |
| Real Sto Return     | -601      |
| Running Env Steps   | 1005000   |
| Running Forward KL  | 34.7      |
| Running Reverse KL  | 4.65      |
| Running Update Time | 201       |
-----------------------------------
-2024-05-13 02:55:00.758039 ʱ--
| Itration            | 202       |
| Loss                | -107      |
| Real Det Return     | -1.86e+03 |
| Real Sto Return     | -547      |
| Running Env Steps   | 1010000   |
| Running Forward KL  | 33.9      |
| Running Reverse KL  | 4.73      |
| Running Update Time | 202       |
-----------------------------------
-2024-05-13 02:57:28.391196 ʱ--
| Itration            | 203       |
| Loss                | -126      |
| Real Det Return     | -2.02e+03 |
| Real Sto Return     | -575      |
| Running Env Steps   | 1015000   |
| Running Forward KL  | 34.2      |
| Running Reverse KL  | 4.53      |
| Running Update Time | 203       |
-----------------------------------
-2024-05-13 02:59:55.892333 ʱ--
| Itration            | 204       |
| Loss                | -93.9     |
| Real Det Return     | -1.93e+03 |
| Real Sto Return     | -617      |
| Running Env Steps   | 1020000   |
| Running Forward KL  | 35.8      |
| Running Reverse KL  | 4.95      |
| Running Update Time | 204       |
-----------------------------------
-2024-05-13 03:02:23.930714 ʱ--
| Itration            | 205       |
| Loss                | -121      |
| Real Det Return     | -1.95e+03 |
| Real Sto Return     | -594      |
| Running Env Steps   | 1025000   |
| Running Forward KL  | 34.3      |
| Running Reverse KL  | 4.43      |
| Running Update Time | 205       |
-----------------------------------
-2024-05-13 03:04:51.569871 ʱ--
| Itration            | 206       |
| Loss                | -132      |
| Real Det Return     | -1.81e+03 |
| Real Sto Return     | -560      |
| Running Env Steps   | 1030000   |
| Running Forward KL  | 35.3      |
| Running Reverse KL  | 4.49      |
| Running Update Time | 206       |
-----------------------------------
-2024-05-13 03:07:19.943596 ʱ--
| Itration            | 207       |
| Loss                | -121      |
| Real Det Return     | -1.87e+03 |
| Real Sto Return     | -572      |
| Running Env Steps   | 1035000   |
| Running Forward KL  | 35.1      |
| Running Reverse KL  | 4.42      |
| Running Update Time | 207       |
-----------------------------------
-2024-05-13 03:09:48.883652 ʱ--
| Itration            | 208       |
| Loss                | -99.3     |
| Real Det Return     | -1.76e+03 |
| Real Sto Return     | -653      |
| Running Env Steps   | 1040000   |
| Running Forward KL  | 35        |
| Running Reverse KL  | 4.46      |
| Running Update Time | 208       |
-----------------------------------
-2024-05-13 03:12:17.955249 ʱ--
| Itration            | 209       |
| Loss                | -106      |
| Real Det Return     | -1.56e+03 |
| Real Sto Return     | -482      |
| Running Env Steps   | 1045000   |
| Running Forward KL  | 35.2      |
| Running Reverse KL  | 4.66      |
| Running Update Time | 209       |
-----------------------------------
-2024-05-13 03:14:47.269375 ʱ--
| Itration            | 210       |
| Loss                | -94.7     |
| Real Det Return     | -1.83e+03 |
| Real Sto Return     | -585      |
| Running Env Steps   | 1050000   |
| Running Forward KL  | 35.8      |
| Running Reverse KL  | 4.72      |
| Running Update Time | 210       |
-----------------------------------
-2024-05-13 03:17:16.564375 ʱ--
| Itration            | 211       |
| Loss                | -93.5     |
| Real Det Return     | -1.73e+03 |
| Real Sto Return     | -536      |
| Running Env Steps   | 1055000   |
| Running Forward KL  | 33.8      |
| Running Reverse KL  | 4.49      |
| Running Update Time | 211       |
-----------------------------------
-2024-05-13 03:19:45.744318 ʱ--
| Itration            | 212       |
| Loss                | -116      |
| Real Det Return     | -1.57e+03 |
| Real Sto Return     | -449      |
| Running Env Steps   | 1060000   |
| Running Forward KL  | 34.7      |
| Running Reverse KL  | 4.47      |
| Running Update Time | 212       |
-----------------------------------
-2024-05-13 03:22:15.238383 ʱ--
| Itration            | 213       |
| Loss                | -141      |
| Real Det Return     | -1.73e+03 |
| Real Sto Return     | -529      |
| Running Env Steps   | 1065000   |
| Running Forward KL  | 35.2      |
| Running Reverse KL  | 5.12      |
| Running Update Time | 213       |
-----------------------------------
-2024-05-13 03:24:45.752225 ʱ--
| Itration            | 214       |
| Loss                | -84.4     |
| Real Det Return     | -1.82e+03 |
| Real Sto Return     | -488      |
| Running Env Steps   | 1070000   |
| Running Forward KL  | 34.7      |
| Running Reverse KL  | 4.64      |
| Running Update Time | 214       |
-----------------------------------
-2024-05-13 03:27:16.432676 ʱ--
| Itration            | 215       |
| Loss                | -111      |
| Real Det Return     | -1.49e+03 |
| Real Sto Return     | -478      |
| Running Env Steps   | 1075000   |
| Running Forward KL  | 34.4      |
| Running Reverse KL  | 4.25      |
| Running Update Time | 215       |
-----------------------------------
-2024-05-13 03:29:46.996635 ʱ--
| Itration            | 216       |
| Loss                | -85.8     |
| Real Det Return     | -1.89e+03 |
| Real Sto Return     | -637      |
| Running Env Steps   | 1080000   |
| Running Forward KL  | 35.9      |
| Running Reverse KL  | 4.39      |
| Running Update Time | 216       |
-----------------------------------
-2024-05-13 03:32:17.994333 ʱ--
| Itration            | 217       |
| Loss                | -149      |
| Real Det Return     | -1.82e+03 |
| Real Sto Return     | -509      |
| Running Env Steps   | 1085000   |
| Running Forward KL  | 35.1      |
| Running Reverse KL  | 4.61      |
| Running Update Time | 217       |
-----------------------------------
-2024-05-13 03:34:49.231410 ʱ--
| Itration            | 218       |
| Loss                | -135      |
| Real Det Return     | -1.47e+03 |
| Real Sto Return     | -411      |
| Running Env Steps   | 1090000   |
| Running Forward KL  | 34.6      |
| Running Reverse KL  | 4.39      |
| Running Update Time | 218       |
-----------------------------------
-2024-05-13 03:37:21.105472 ʱ--
| Itration            | 219       |
| Loss                | -95       |
| Real Det Return     | -1.54e+03 |
| Real Sto Return     | -417      |
| Running Env Steps   | 1095000   |
| Running Forward KL  | 34.5      |
| Running Reverse KL  | 4.5       |
| Running Update Time | 219       |
-----------------------------------
-2024-05-13 03:39:52.604135 ʱ--
| Itration            | 220       |
| Loss                | -121      |
| Real Det Return     | -1.56e+03 |
| Real Sto Return     | -469      |
| Running Env Steps   | 1100000   |
| Running Forward KL  | 33.8      |
| Running Reverse KL  | 4.19      |
| Running Update Time | 220       |
-----------------------------------
-2024-05-13 03:42:25.177232 ʱ--
| Itration            | 221       |
| Loss                | -143      |
| Real Det Return     | -1.67e+03 |
| Real Sto Return     | -485      |
| Running Env Steps   | 1105000   |
| Running Forward KL  | 34.4      |
| Running Reverse KL  | 4.4       |
| Running Update Time | 221       |
-----------------------------------
-2024-05-13 03:44:57.625606 ʱ--
| Itration            | 222       |
| Loss                | -142      |
| Real Det Return     | -1.58e+03 |
| Real Sto Return     | -474      |
| Running Env Steps   | 1110000   |
| Running Forward KL  | 34.2      |
| Running Reverse KL  | 4.24      |
| Running Update Time | 222       |
-----------------------------------
-2024-05-13 03:47:29.386010 ʱ--
| Itration            | 223       |
| Loss                | -127      |
| Real Det Return     | -1.42e+03 |
| Real Sto Return     | -394      |
| Running Env Steps   | 1115000   |
| Running Forward KL  | 33.6      |
| Running Reverse KL  | 4.13      |
| Running Update Time | 223       |
-----------------------------------
-2024-05-13 03:50:02.240861 ʱ--
| Itration            | 224       |
| Loss                | -113      |
| Real Det Return     | -1.73e+03 |
| Real Sto Return     | -468      |
| Running Env Steps   | 1120000   |
| Running Forward KL  | 34.4      |
| Running Reverse KL  | 4.42      |
| Running Update Time | 224       |
-----------------------------------
-2024-05-13 03:52:34.955146 ʱ--
| Itration            | 225       |
| Loss                | -118      |
| Real Det Return     | -1.48e+03 |
| Real Sto Return     | -432      |
| Running Env Steps   | 1125000   |
| Running Forward KL  | 34.2      |
| Running Reverse KL  | 4.44      |
| Running Update Time | 225       |
-----------------------------------
-2024-05-13 03:55:08.140019 ʱ--
| Itration            | 226       |
| Loss                | -119      |
| Real Det Return     | -1.38e+03 |
| Real Sto Return     | -453      |
| Running Env Steps   | 1130000   |
| Running Forward KL  | 33.8      |
| Running Reverse KL  | 4.37      |
| Running Update Time | 226       |
-----------------------------------
-2024-05-13 03:57:40.667615 ʱ-
| Itration            | 227      |
| Loss                | -157     |
| Real Det Return     | -1.5e+03 |
| Real Sto Return     | -503     |
| Running Env Steps   | 1135000  |
| Running Forward KL  | 33.8     |
| Running Reverse KL  | 3.95     |
| Running Update Time | 227      |
----------------------------------
-2024-05-13 04:00:14.396945 ʱ--
| Itration            | 228       |
| Loss                | -123      |
| Real Det Return     | -1.33e+03 |
| Real Sto Return     | -387      |
| Running Env Steps   | 1140000   |
| Running Forward KL  | 34        |
| Running Reverse KL  | 4.38      |
| Running Update Time | 228       |
-----------------------------------
-2024-05-13 04:02:47.890793 ʱ-
| Itration            | 229      |
| Loss                | -134     |
| Real Det Return     | -1.7e+03 |
| Real Sto Return     | -462     |
| Running Env Steps   | 1145000  |
| Running Forward KL  | 32.7     |
| Running Reverse KL  | 4.42     |
| Running Update Time | 229      |
----------------------------------
-2024-05-13 04:05:21.774314 ʱ--
| Itration            | 230       |
| Loss                | -83.2     |
| Real Det Return     | -1.72e+03 |
| Real Sto Return     | -477      |
| Running Env Steps   | 1150000   |
| Running Forward KL  | 33.1      |
| Running Reverse KL  | 4.13      |
| Running Update Time | 230       |
-----------------------------------
-2024-05-13 04:07:55.610775 ʱ--
| Itration            | 231       |
| Loss                | -134      |
| Real Det Return     | -1.46e+03 |
| Real Sto Return     | -447      |
| Running Env Steps   | 1155000   |
| Running Forward KL  | 33.9      |
| Running Reverse KL  | 4.22      |
| Running Update Time | 231       |
-----------------------------------
-2024-05-13 04:10:30.177405 ʱ--
| Itration            | 232       |
| Loss                | -156      |
| Real Det Return     | -1.62e+03 |
| Real Sto Return     | -447      |
| Running Env Steps   | 1160000   |
| Running Forward KL  | 33.6      |
| Running Reverse KL  | 4.17      |
| Running Update Time | 232       |
-----------------------------------
-2024-05-13 04:13:03.977851 ʱ--
| Itration            | 233       |
| Loss                | -118      |
| Real Det Return     | -1.34e+03 |
| Real Sto Return     | -399      |
| Running Env Steps   | 1165000   |
| Running Forward KL  | 33.8      |
| Running Reverse KL  | 4.24      |
| Running Update Time | 233       |
-----------------------------------
-2024-05-13 04:15:38.172069 ʱ--
| Itration            | 234       |
| Loss                | -135      |
| Real Det Return     | -1.05e+03 |
| Real Sto Return     | -361      |
| Running Env Steps   | 1170000   |
| Running Forward KL  | 33.9      |
| Running Reverse KL  | 4.1       |
| Running Update Time | 234       |
-----------------------------------
-2024-05-13 04:18:13.183240 ʱ--
| Itration            | 235       |
| Loss                | -133      |
| Real Det Return     | -1.35e+03 |
| Real Sto Return     | -439      |
| Running Env Steps   | 1175000   |
| Running Forward KL  | 34        |
| Running Reverse KL  | 4.48      |
| Running Update Time | 235       |
-----------------------------------
-2024-05-13 04:20:48.644498 ʱ-
| Itration            | 236      |
| Loss                | -95      |
| Real Det Return     | -707     |
| Real Sto Return     | -381     |
| Running Env Steps   | 1180000  |
| Running Forward KL  | 33.4     |
| Running Reverse KL  | 4.38     |
| Running Update Time | 236      |
----------------------------------
-2024-05-13 04:23:24.052926 ʱ-
| Itration            | 237      |
| Loss                | -81.2    |
| Real Det Return     | -969     |
| Real Sto Return     | -357     |
| Running Env Steps   | 1185000  |
| Running Forward KL  | 32.9     |
| Running Reverse KL  | 4.25     |
| Running Update Time | 237      |
----------------------------------
-2024-05-13 04:25:58.799423 ʱ--
| Itration            | 238       |
| Loss                | -128      |
| Real Det Return     | -1.11e+03 |
| Real Sto Return     | -381      |
| Running Env Steps   | 1190000   |
| Running Forward KL  | 33.3      |
| Running Reverse KL  | 4.39      |
| Running Update Time | 238       |
-----------------------------------
-2024-05-13 04:28:34.065516 ʱ--
| Itration            | 239       |
| Loss                | -164      |
| Real Det Return     | -1.14e+03 |
| Real Sto Return     | -353      |
| Running Env Steps   | 1195000   |
| Running Forward KL  | 33.3      |
| Running Reverse KL  | 4.24      |
| Running Update Time | 239       |
-----------------------------------
-2024-05-13 04:31:09.445858 ʱ--
| Itration            | 240       |
| Loss                | -171      |
| Real Det Return     | -1.44e+03 |
| Real Sto Return     | -404      |
| Running Env Steps   | 1200000   |
| Running Forward KL  | 34.1      |
| Running Reverse KL  | 4.36      |
| Running Update Time | 240       |
-----------------------------------
-2024-05-13 04:33:44.939231 ʱ--
| Itration            | 241       |
| Loss                | -153      |
| Real Det Return     | -1.43e+03 |
| Real Sto Return     | -489      |
| Running Env Steps   | 1205000   |
| Running Forward KL  | 33.6      |
| Running Reverse KL  | 3.95      |
| Running Update Time | 241       |
-----------------------------------
-2024-05-13 04:36:21.186739 ʱ--
| Itration            | 242       |
| Loss                | -161      |
| Real Det Return     | -1.66e+03 |
| Real Sto Return     | -420      |
| Running Env Steps   | 1210000   |
| Running Forward KL  | 34.4      |
| Running Reverse KL  | 4.29      |
| Running Update Time | 242       |
-----------------------------------
-2024-05-13 04:38:56.771702 ʱ-
| Itration            | 243      |
| Loss                | -140     |
| Real Det Return     | -997     |
| Real Sto Return     | -351     |
| Running Env Steps   | 1215000  |
| Running Forward KL  | 33.6     |
| Running Reverse KL  | 4.03     |
| Running Update Time | 243      |
----------------------------------
-2024-05-13 04:41:32.822201 ʱ-
| Itration            | 244      |
| Loss                | -174     |
| Real Det Return     | -1.2e+03 |
| Real Sto Return     | -364     |
| Running Env Steps   | 1220000  |
| Running Forward KL  | 33.4     |
| Running Reverse KL  | 4.1      |
| Running Update Time | 244      |
----------------------------------
-2024-05-13 04:44:08.217538 ʱ--
| Itration            | 245       |
| Loss                | -151      |
| Real Det Return     | -1.47e+03 |
| Real Sto Return     | -449      |
| Running Env Steps   | 1225000   |
| Running Forward KL  | 33.4      |
| Running Reverse KL  | 4.19      |
| Running Update Time | 245       |
-----------------------------------
-2024-05-13 04:46:43.572153 ʱ-
| Itration            | 246      |
| Loss                | -167     |
| Real Det Return     | -1.1e+03 |
| Real Sto Return     | -365     |
| Running Env Steps   | 1230000  |
| Running Forward KL  | 33       |
| Running Reverse KL  | 4.14     |
| Running Update Time | 246      |
----------------------------------
-2024-05-13 04:49:19.458219 ʱ--
| Itration            | 247       |
| Loss                | -145      |
| Real Det Return     | -1.32e+03 |
| Real Sto Return     | -436      |
| Running Env Steps   | 1235000   |
| Running Forward KL  | 33        |
| Running Reverse KL  | 4.03      |
| Running Update Time | 247       |
-----------------------------------
-2024-05-13 04:51:55.972438 ʱ--
| Itration            | 248       |
| Loss                | -132      |
| Real Det Return     | -1.35e+03 |
| Real Sto Return     | -372      |
| Running Env Steps   | 1240000   |
| Running Forward KL  | 33        |
| Running Reverse KL  | 3.98      |
| Running Update Time | 248       |
-----------------------------------
-2024-05-13 04:54:32.432781 ʱ--
| Itration            | 249       |
| Loss                | -132      |
| Real Det Return     | -1.34e+03 |
| Real Sto Return     | -450      |
| Running Env Steps   | 1245000   |
| Running Forward KL  | 32.9      |
| Running Reverse KL  | 4.15      |
| Running Update Time | 249       |
-----------------------------------
-2024-05-13 04:57:08.737741 ʱ--
| Itration            | 250       |
| Loss                | -189      |
| Real Det Return     | -1.21e+03 |
| Real Sto Return     | -358      |
| Running Env Steps   | 1250000   |
| Running Forward KL  | 32.5      |
| Running Reverse KL  | 3.74      |
| Running Update Time | 250       |
-----------------------------------
-2024-05-13 04:59:45.582529 ʱ--
| Itration            | 251       |
| Loss                | -150      |
| Real Det Return     | -1.14e+03 |
| Real Sto Return     | -370      |
| Running Env Steps   | 1255000   |
| Running Forward KL  | 32.3      |
| Running Reverse KL  | 3.75      |
| Running Update Time | 251       |
-----------------------------------
-2024-05-13 05:02:22.234375 ʱ--
| Itration            | 252       |
| Loss                | -169      |
| Real Det Return     | -1.19e+03 |
| Real Sto Return     | -411      |
| Running Env Steps   | 1260000   |
| Running Forward KL  | 33        |
| Running Reverse KL  | 4.01      |
| Running Update Time | 252       |
-----------------------------------
-2024-05-13 05:04:58.372904 ʱ-
| Itration            | 253      |
| Loss                | -147     |
| Real Det Return     | -971     |
| Real Sto Return     | -370     |
| Running Env Steps   | 1265000  |
| Running Forward KL  | 32.7     |
| Running Reverse KL  | 3.88     |
| Running Update Time | 253      |
----------------------------------
-2024-05-13 05:07:35.203189 ʱ-
| Itration            | 254      |
| Loss                | -109     |
| Real Det Return     | -923     |
| Real Sto Return     | -354     |
| Running Env Steps   | 1270000  |
| Running Forward KL  | 33.1     |
| Running Reverse KL  | 4.11     |
| Running Update Time | 254      |
----------------------------------
-2024-05-13 05:10:11.650388 ʱ--
| Itration            | 255       |
| Loss                | -115      |
| Real Det Return     | -1.17e+03 |
| Real Sto Return     | -371      |
| Running Env Steps   | 1275000   |
| Running Forward KL  | 32.4      |
| Running Reverse KL  | 3.79      |
| Running Update Time | 255       |
-----------------------------------
-2024-05-13 05:12:47.981616 ʱ--
| Itration            | 256       |
| Loss                | -129      |
| Real Det Return     | -1.17e+03 |
| Real Sto Return     | -369      |
| Running Env Steps   | 1280000   |
| Running Forward KL  | 32.6      |
| Running Reverse KL  | 4.03      |
| Running Update Time | 256       |
-----------------------------------
-2024-05-13 05:15:25.198936 ʱ--
| Itration            | 257       |
| Loss                | -151      |
| Real Det Return     | -1.19e+03 |
| Real Sto Return     | -400      |
| Running Env Steps   | 1285000   |
| Running Forward KL  | 32.8      |
| Running Reverse KL  | 3.92      |
| Running Update Time | 257       |
-----------------------------------
-2024-05-13 05:18:03.194234 ʱ--
| Itration            | 258       |
| Loss                | -116      |
| Real Det Return     | -1.37e+03 |
| Real Sto Return     | -454      |
| Running Env Steps   | 1290000   |
| Running Forward KL  | 32.7      |
| Running Reverse KL  | 3.96      |
| Running Update Time | 258       |
-----------------------------------
-2024-05-13 05:20:40.143863 ʱ--
| Itration            | 259       |
| Loss                | -151      |
| Real Det Return     | -1.11e+03 |
| Real Sto Return     | -368      |
| Running Env Steps   | 1295000   |
| Running Forward KL  | 32.4      |
| Running Reverse KL  | 3.78      |
| Running Update Time | 259       |
-----------------------------------
-2024-05-13 05:23:16.666239 ʱ--
| Itration            | 260       |
| Loss                | -153      |
| Real Det Return     | -1.23e+03 |
| Real Sto Return     | -386      |
| Running Env Steps   | 1300000   |
| Running Forward KL  | 32.8      |
| Running Reverse KL  | 3.74      |
| Running Update Time | 260       |
-----------------------------------
-2024-05-13 05:25:54.336275 ʱ--
| Itration            | 261       |
| Loss                | -138      |
| Real Det Return     | -1.19e+03 |
| Real Sto Return     | -395      |
| Running Env Steps   | 1305000   |
| Running Forward KL  | 33.2      |
| Running Reverse KL  | 3.77      |
| Running Update Time | 261       |
-----------------------------------
-2024-05-13 05:28:31.639310 ʱ--
| Itration            | 262       |
| Loss                | -141      |
| Real Det Return     | -1.21e+03 |
| Real Sto Return     | -411      |
| Running Env Steps   | 1310000   |
| Running Forward KL  | 33.6      |
| Running Reverse KL  | 4.1       |
| Running Update Time | 262       |
-----------------------------------
-2024-05-13 05:31:11.886009 ʱ--
| Itration            | 263       |
| Loss                | -171      |
| Real Det Return     | -1.19e+03 |
| Real Sto Return     | -386      |
| Running Env Steps   | 1315000   |
| Running Forward KL  | 32.7      |
| Running Reverse KL  | 3.83      |
| Running Update Time | 263       |
-----------------------------------
-2024-05-13 05:33:49.830406 ʱ--
| Itration            | 264       |
| Loss                | -159      |
| Real Det Return     | -1.25e+03 |
| Real Sto Return     | -389      |
| Running Env Steps   | 1320000   |
| Running Forward KL  | 32.6      |
| Running Reverse KL  | 3.72      |
| Running Update Time | 264       |
-----------------------------------
-2024-05-13 05:36:27.638183 ʱ--
| Itration            | 265       |
| Loss                | -150      |
| Real Det Return     | -1.05e+03 |
| Real Sto Return     | -377      |
| Running Env Steps   | 1325000   |
| Running Forward KL  | 32.8      |
| Running Reverse KL  | 3.73      |
| Running Update Time | 265       |
-----------------------------------
-2024-05-13 05:39:04.899544 ʱ--
| Itration            | 266       |
| Loss                | -134      |
| Real Det Return     | -1.21e+03 |
| Real Sto Return     | -373      |
| Running Env Steps   | 1330000   |
| Running Forward KL  | 31.8      |
| Running Reverse KL  | 3.57      |
| Running Update Time | 266       |
-----------------------------------
-2024-05-13 05:41:42.254479 ʱ--
| Itration            | 267       |
| Loss                | -134      |
| Real Det Return     | -1.02e+03 |
| Real Sto Return     | -349      |
| Running Env Steps   | 1335000   |
| Running Forward KL  | 31.9      |
| Running Reverse KL  | 3.68      |
| Running Update Time | 267       |
-----------------------------------
-2024-05-13 05:44:19.741306 ʱ--
| Itration            | 268       |
| Loss                | -126      |
| Real Det Return     | -1.08e+03 |
| Real Sto Return     | -330      |
| Running Env Steps   | 1340000   |
| Running Forward KL  | 32.4      |
| Running Reverse KL  | 3.72      |
| Running Update Time | 268       |
-----------------------------------
-2024-05-13 05:46:56.672995 ʱ--
| Itration            | 269       |
| Loss                | -151      |
| Real Det Return     | -1.15e+03 |
| Real Sto Return     | -375      |
| Running Env Steps   | 1345000   |
| Running Forward KL  | 32.1      |
| Running Reverse KL  | 3.57      |
| Running Update Time | 269       |
-----------------------------------
-2024-05-13 05:49:34.511937 ʱ-
| Itration            | 270      |
| Loss                | -184     |
| Real Det Return     | -887     |
| Real Sto Return     | -322     |
| Running Env Steps   | 1350000  |
| Running Forward KL  | 32.3     |
| Running Reverse KL  | 3.61     |
| Running Update Time | 270      |
----------------------------------
-2024-05-13 05:52:12.165206 ʱ--
| Itration            | 271       |
| Loss                | -149      |
| Real Det Return     | -1.11e+03 |
| Real Sto Return     | -378      |
| Running Env Steps   | 1355000   |
| Running Forward KL  | 32.4      |
| Running Reverse KL  | 3.58      |
| Running Update Time | 271       |
-----------------------------------
-2024-05-13 05:54:50.180700 ʱ--
| Itration            | 272       |
| Loss                | -169      |
| Real Det Return     | -1.28e+03 |
| Real Sto Return     | -433      |
| Running Env Steps   | 1360000   |
| Running Forward KL  | 32.6      |
| Running Reverse KL  | 3.86      |
| Running Update Time | 272       |
-----------------------------------
-2024-05-13 05:57:28.110746 ʱ--
| Itration            | 273       |
| Loss                | -187      |
| Real Det Return     | -1.05e+03 |
| Real Sto Return     | -339      |
| Running Env Steps   | 1365000   |
| Running Forward KL  | 31.7      |
| Running Reverse KL  | 3.58      |
| Running Update Time | 273       |
-----------------------------------
-2024-05-13 06:00:06.336208 ʱ-
| Itration            | 274      |
| Loss                | -149     |
| Real Det Return     | -1.1e+03 |
| Real Sto Return     | -348     |
| Running Env Steps   | 1370000  |
| Running Forward KL  | 31.5     |
| Running Reverse KL  | 3.54     |
| Running Update Time | 274      |
----------------------------------
-2024-05-13 06:02:43.590217 ʱ--
| Itration            | 275       |
| Loss                | -140      |
| Real Det Return     | -1.21e+03 |
| Real Sto Return     | -391      |
| Running Env Steps   | 1375000   |
| Running Forward KL  | 32.3      |
| Running Reverse KL  | 3.72      |
| Running Update Time | 275       |
-----------------------------------
-2024-05-13 06:05:21.819830 ʱ--
| Itration            | 276       |
| Loss                | -177      |
| Real Det Return     | -1.25e+03 |
| Real Sto Return     | -434      |
| Running Env Steps   | 1380000   |
| Running Forward KL  | 32.2      |
| Running Reverse KL  | 3.56      |
| Running Update Time | 276       |
-----------------------------------
-2024-05-13 06:07:59.754724 ʱ-
| Itration            | 277      |
| Loss                | -143     |
| Real Det Return     | -983     |
| Real Sto Return     | -320     |
| Running Env Steps   | 1385000  |
| Running Forward KL  | 31.7     |
| Running Reverse KL  | 3.74     |
| Running Update Time | 277      |
----------------------------------
-2024-05-13 06:10:37.682006 ʱ-
| Itration            | 278      |
| Loss                | -142     |
| Real Det Return     | -925     |
| Real Sto Return     | -377     |
| Running Env Steps   | 1390000  |
| Running Forward KL  | 31.5     |
| Running Reverse KL  | 3.49     |
| Running Update Time | 278      |
----------------------------------
-2024-05-13 06:13:15.931387 ʱ-
| Itration            | 279      |
| Loss                | -206     |
| Real Det Return     | -919     |
| Real Sto Return     | -325     |
| Running Env Steps   | 1395000  |
| Running Forward KL  | 31.6     |
| Running Reverse KL  | 3.74     |
| Running Update Time | 279      |
----------------------------------
-2024-05-13 06:15:54.263075 ʱ--
| Itration            | 280       |
| Loss                | -181      |
| Real Det Return     | -1.07e+03 |
| Real Sto Return     | -354      |
| Running Env Steps   | 1400000   |
| Running Forward KL  | 32.3      |
| Running Reverse KL  | 3.72      |
| Running Update Time | 280       |
-----------------------------------
-2024-05-13 06:18:32.090570 ʱ-
| Itration            | 281      |
| Loss                | -122     |
| Real Det Return     | -938     |
| Real Sto Return     | -405     |
| Running Env Steps   | 1405000  |
| Running Forward KL  | 32.3     |
| Running Reverse KL  | 3.55     |
| Running Update Time | 281      |
----------------------------------
-2024-05-13 06:21:10.615100 ʱ-
| Itration            | 282      |
| Loss                | -150     |
| Real Det Return     | -1.1e+03 |
| Real Sto Return     | -391     |
| Running Env Steps   | 1410000  |
| Running Forward KL  | 32.3     |
| Running Reverse KL  | 3.76     |
| Running Update Time | 282      |
----------------------------------
-2024-05-13 06:23:48.144382 ʱ--
| Itration            | 283       |
| Loss                | -180      |
| Real Det Return     | -1.17e+03 |
| Real Sto Return     | -358      |
| Running Env Steps   | 1415000   |
| Running Forward KL  | 31.7      |
| Running Reverse KL  | 3.47      |
| Running Update Time | 283       |
-----------------------------------
-2024-05-13 06:26:26.325570 ʱ-
| Itration            | 284      |
| Loss                | -170     |
| Real Det Return     | -893     |
| Real Sto Return     | -352     |
| Running Env Steps   | 1420000  |
| Running Forward KL  | 31.7     |
| Running Reverse KL  | 3.43     |
| Running Update Time | 284      |
----------------------------------
-2024-05-13 06:29:04.402737 ʱ--
| Itration            | 285       |
| Loss                | -153      |
| Real Det Return     | -1.09e+03 |
| Real Sto Return     | -371      |
| Running Env Steps   | 1425000   |
| Running Forward KL  | 32.5      |
| Running Reverse KL  | 3.67      |
| Running Update Time | 285       |
-----------------------------------
-2024-05-13 06:31:42.468158 ʱ--
| Itration            | 286       |
| Loss                | -191      |
| Real Det Return     | -1.18e+03 |
| Real Sto Return     | -378      |
| Running Env Steps   | 1430000   |
| Running Forward KL  | 31.5      |
| Running Reverse KL  | 3.73      |
| Running Update Time | 286       |
-----------------------------------
-2024-05-13 06:34:20.493324 ʱ-
| Itration            | 287      |
| Loss                | -164     |
| Real Det Return     | -889     |
| Real Sto Return     | -338     |
| Running Env Steps   | 1435000  |
| Running Forward KL  | 31.5     |
| Running Reverse KL  | 3.58     |
| Running Update Time | 287      |
----------------------------------
-2024-05-13 06:36:58.895664 ʱ--
| Itration            | 288       |
| Loss                | -133      |
| Real Det Return     | -1.32e+03 |
| Real Sto Return     | -405      |
| Running Env Steps   | 1440000   |
| Running Forward KL  | 30.9      |
| Running Reverse KL  | 3.59      |
| Running Update Time | 288       |
-----------------------------------
-2024-05-13 06:39:37.110649 ʱ-
| Itration            | 289      |
| Loss                | -179     |
| Real Det Return     | -718     |
| Real Sto Return     | -293     |
| Running Env Steps   | 1445000  |
| Running Forward KL  | 32.1     |
| Running Reverse KL  | 3.81     |
| Running Update Time | 289      |
----------------------------------
-2024-05-13 06:42:15.542635 ʱ-
| Itration            | 290      |
| Loss                | -160     |
| Real Det Return     | -967     |
| Real Sto Return     | -363     |
| Running Env Steps   | 1450000  |
| Running Forward KL  | 31.7     |
| Running Reverse KL  | 3.71     |
| Running Update Time | 290      |
----------------------------------
-2024-05-13 06:44:53.977473 ʱ--
| Itration            | 291       |
| Loss                | -152      |
| Real Det Return     | -1.21e+03 |
| Real Sto Return     | -465      |
| Running Env Steps   | 1455000   |
| Running Forward KL  | 31.8      |
| Running Reverse KL  | 3.69      |
| Running Update Time | 291       |
-----------------------------------
-2024-05-13 06:47:32.146899 ʱ-
| Itration            | 292      |
| Loss                | -133     |
| Real Det Return     | -1.1e+03 |
| Real Sto Return     | -410     |
| Running Env Steps   | 1460000  |
| Running Forward KL  | 31.1     |
| Running Reverse KL  | 3.39     |
| Running Update Time | 292      |
----------------------------------
-2024-05-13 06:50:10.895763 ʱ--
| Itration            | 293       |
| Loss                | -164      |
| Real Det Return     | -1.11e+03 |
| Real Sto Return     | -356      |
| Running Env Steps   | 1465000   |
| Running Forward KL  | 31.3      |
| Running Reverse KL  | 3.59      |
| Running Update Time | 293       |
-----------------------------------
-2024-05-13 06:52:49.081296 ʱ-
| Itration            | 294      |
| Loss                | -143     |
| Real Det Return     | -1.1e+03 |
| Real Sto Return     | -423     |
| Running Env Steps   | 1470000  |
| Running Forward KL  | 31.9     |
| Running Reverse KL  | 3.72     |
| Running Update Time | 294      |
----------------------------------
-2024-05-13 06:55:27.459985 ʱ--
| Itration            | 295       |
| Loss                | -165      |
| Real Det Return     | -1.15e+03 |
| Real Sto Return     | -405      |
| Running Env Steps   | 1475000   |
| Running Forward KL  | 31.5      |
| Running Reverse KL  | 3.67      |
| Running Update Time | 295       |
-----------------------------------
-2024-05-13 06:58:06.016590 ʱ--
| Itration            | 296       |
| Loss                | -182      |
| Real Det Return     | -1.02e+03 |
| Real Sto Return     | -370      |
| Running Env Steps   | 1480000   |
| Running Forward KL  | 32        |
| Running Reverse KL  | 3.66      |
| Running Update Time | 296       |
-----------------------------------
-2024-05-13 07:00:44.910344 ʱ--
| Itration            | 297       |
| Loss                | -167      |
| Real Det Return     | -1.08e+03 |
| Real Sto Return     | -395      |
| Running Env Steps   | 1485000   |
| Running Forward KL  | 31.5      |
| Running Reverse KL  | 3.65      |
| Running Update Time | 297       |
-----------------------------------
-2024-05-13 07:03:23.849281 ʱ--
| Itration            | 298       |
| Loss                | -184      |
| Real Det Return     | -1.03e+03 |
| Real Sto Return     | -377      |
| Running Env Steps   | 1490000   |
| Running Forward KL  | 31.2      |
| Running Reverse KL  | 3.42      |
| Running Update Time | 298       |
-----------------------------------
-2024-05-13 07:06:03.147584 ʱ-
| Itration            | 299      |
| Loss                | -161     |
| Real Det Return     | -956     |
| Real Sto Return     | -328     |
| Running Env Steps   | 1495000  |
| Running Forward KL  | 31.5     |
| Running Reverse KL  | 3.68     |
| Running Update Time | 299      |
----------------------------------
-2024-05-13 07:08:41.122441 ʱ-
| Itration            | 300      |
| Loss                | -174     |
| Real Det Return     | -766     |
| Real Sto Return     | -322     |
| Running Env Steps   | 1500000  |
| Running Forward KL  | 31.2     |
| Running Reverse KL  | 3.65     |
| Running Update Time | 300      |
----------------------------------
-2024-05-13 07:11:05.263144 ʱ--
| Itration            | 301       |
| Loss                | -170      |
| Real Det Return     | -1.24e+03 |
| Real Sto Return     | -458      |
| Running Env Steps   | 1505000   |
| Running Forward KL  | 31.6      |
| Running Reverse KL  | 3.76      |
| Running Update Time | 301       |
-----------------------------------
-2024-05-13 07:13:29.124020 ʱ--
| Itration            | 302       |
| Loss                | -169      |
| Real Det Return     | -1.12e+03 |
| Real Sto Return     | -361      |
| Running Env Steps   | 1510000   |
| Running Forward KL  | 31.2      |
| Running Reverse KL  | 3.39      |
| Running Update Time | 302       |
-----------------------------------
-2024-05-13 07:15:53.049147 ʱ-
| Itration            | 303      |
| Loss                | -201     |
| Real Det Return     | -875     |
| Real Sto Return     | -351     |
| Running Env Steps   | 1515000  |
| Running Forward KL  | 31.2     |
| Running Reverse KL  | 3.45     |
| Running Update Time | 303      |
----------------------------------
-2024-05-13 07:18:17.360192 ʱ-
| Itration            | 304      |
| Loss                | -157     |
| Real Det Return     | -905     |
| Real Sto Return     | -366     |
| Running Env Steps   | 1520000  |
| Running Forward KL  | 31.4     |
| Running Reverse KL  | 3.71     |
| Running Update Time | 304      |
----------------------------------
-2024-05-13 07:20:41.696083 ʱ--
| Itration            | 305       |
| Loss                | -200      |
| Real Det Return     | -1.16e+03 |
| Real Sto Return     | -408      |
| Running Env Steps   | 1525000   |
| Running Forward KL  | 31.3      |
| Running Reverse KL  | 3.94      |
| Running Update Time | 305       |
-----------------------------------
-2024-05-13 07:23:05.745435 ʱ-
| Itration            | 306      |
| Loss                | -199     |
| Real Det Return     | -713     |
| Real Sto Return     | -308     |
| Running Env Steps   | 1530000  |
| Running Forward KL  | 31.1     |
| Running Reverse KL  | 3.51     |
| Running Update Time | 306      |
----------------------------------
-2024-05-13 07:25:29.632247 ʱ--
| Itration            | 307       |
| Loss                | -144      |
| Real Det Return     | -1.12e+03 |
| Real Sto Return     | -377      |
| Running Env Steps   | 1535000   |
| Running Forward KL  | 30.9      |
| Running Reverse KL  | 3.18      |
| Running Update Time | 307       |
-----------------------------------
-2024-05-13 07:27:53.767155 ʱ-
| Itration            | 308      |
| Loss                | -127     |
| Real Det Return     | -887     |
| Real Sto Return     | -322     |
| Running Env Steps   | 1540000  |
| Running Forward KL  | 30       |
| Running Reverse KL  | 3.48     |
| Running Update Time | 308      |
----------------------------------
-2024-05-13 07:30:18.055794 ʱ-
| Itration            | 309      |
| Loss                | -175     |
| Real Det Return     | -952     |
| Real Sto Return     | -325     |
| Running Env Steps   | 1545000  |
| Running Forward KL  | 30.9     |
| Running Reverse KL  | 3.41     |
| Running Update Time | 309      |
----------------------------------
-2024-05-13 07:32:42.222185 ʱ-
| Itration            | 310      |
| Loss                | -174     |
| Real Det Return     | -783     |
| Real Sto Return     | -279     |
| Running Env Steps   | 1550000  |
| Running Forward KL  | 30.8     |
| Running Reverse KL  | 3.15     |
| Running Update Time | 310      |
----------------------------------
-2024-05-13 07:35:06.156624 ʱ--
| Itration            | 311       |
| Loss                | -151      |
| Real Det Return     | -1.18e+03 |
| Real Sto Return     | -386      |
| Running Env Steps   | 1555000   |
| Running Forward KL  | 30.9      |
| Running Reverse KL  | 3.59      |
| Running Update Time | 311       |
-----------------------------------
-2024-05-13 07:37:29.927402 ʱ--
| Itration            | 312       |
| Loss                | -149      |
| Real Det Return     | -1.01e+03 |
| Real Sto Return     | -393      |
| Running Env Steps   | 1560000   |
| Running Forward KL  | 30.6      |
| Running Reverse KL  | 3.22      |
| Running Update Time | 312       |
-----------------------------------
-2024-05-13 07:39:53.565133 ʱ--
| Itration            | 313       |
| Loss                | -193      |
| Real Det Return     | -1.03e+03 |
| Real Sto Return     | -411      |
| Running Env Steps   | 1565000   |
| Running Forward KL  | 31.6      |
| Running Reverse KL  | 3.55      |
| Running Update Time | 313       |
-----------------------------------
-2024-05-13 07:42:17.600479 ʱ-
| Itration            | 314      |
| Loss                | -159     |
| Real Det Return     | -1.1e+03 |
| Real Sto Return     | -374     |
| Running Env Steps   | 1570000  |
| Running Forward KL  | 31.7     |
| Running Reverse KL  | 3.38     |
| Running Update Time | 314      |
----------------------------------
-2024-05-13 07:44:41.975310 ʱ--
| Itration            | 315       |
| Loss                | -186      |
| Real Det Return     | -1.28e+03 |
| Real Sto Return     | -362      |
| Running Env Steps   | 1575000   |
| Running Forward KL  | 31.7      |
| Running Reverse KL  | 3.57      |
| Running Update Time | 315       |
-----------------------------------
-2024-05-13 07:47:06.459441 ʱ-
| Itration            | 316      |
| Loss                | -162     |
| Real Det Return     | -735     |
| Real Sto Return     | -314     |
| Running Env Steps   | 1580000  |
| Running Forward KL  | 30.1     |
| Running Reverse KL  | 3.21     |
| Running Update Time | 316      |
----------------------------------
-2024-05-13 07:49:30.671092 ʱ--
| Itration            | 317       |
| Loss                | -169      |
| Real Det Return     | -1.06e+03 |
| Real Sto Return     | -466      |
| Running Env Steps   | 1585000   |
| Running Forward KL  | 30.9      |
| Running Reverse KL  | 3.3       |
| Running Update Time | 317       |
-----------------------------------
-2024-05-13 07:51:55.107843 ʱ-
| Itration            | 318      |
| Loss                | -147     |
| Real Det Return     | -932     |
| Real Sto Return     | -352     |
| Running Env Steps   | 1590000  |
| Running Forward KL  | 31.3     |
| Running Reverse KL  | 3.65     |
| Running Update Time | 318      |
----------------------------------
-2024-05-13 07:54:19.538198 ʱ-
| Itration            | 319      |
| Loss                | -174     |
| Real Det Return     | -864     |
| Real Sto Return     | -328     |
| Running Env Steps   | 1595000  |
| Running Forward KL  | 30.9     |
| Running Reverse KL  | 3.31     |
| Running Update Time | 319      |
----------------------------------
-2024-05-13 07:56:43.950345 ʱ--
| Itration            | 320       |
| Loss                | -162      |
| Real Det Return     | -1.18e+03 |
| Real Sto Return     | -379      |
| Running Env Steps   | 1600000   |
| Running Forward KL  | 31.3      |
| Running Reverse KL  | 3.54      |
| Running Update Time | 320       |
-----------------------------------
-2024-05-13 07:59:08.529278 ʱ-
| Itration            | 321      |
| Loss                | -175     |
| Real Det Return     | -472     |
| Real Sto Return     | -293     |
| Running Env Steps   | 1605000  |
| Running Forward KL  | 30       |
| Running Reverse KL  | 3.3      |
| Running Update Time | 321      |
----------------------------------
-2024-05-13 08:01:33.421053 ʱ--
| Itration            | 322       |
| Loss                | -196      |
| Real Det Return     | -1.01e+03 |
| Real Sto Return     | -380      |
| Running Env Steps   | 1610000   |
| Running Forward KL  | 30.9      |
| Running Reverse KL  | 3.28      |
| Running Update Time | 322       |
-----------------------------------
-2024-05-13 08:04:03.716492 ʱ-
| Itration            | 323      |
| Loss                | -165     |
| Real Det Return     | -950     |
| Real Sto Return     | -334     |
| Running Env Steps   | 1615000  |
| Running Forward KL  | 31       |
| Running Reverse KL  | 3.51     |
| Running Update Time | 323      |
----------------------------------
-2024-05-13 08:06:28.268859 ʱ-
| Itration            | 324      |
| Loss                | -165     |
| Real Det Return     | -735     |
| Real Sto Return     | -301     |
| Running Env Steps   | 1620000  |
| Running Forward KL  | 30.3     |
| Running Reverse KL  | 3.21     |
| Running Update Time | 324      |
----------------------------------
-2024-05-13 08:08:52.758544 ʱ-
| Itration            | 325      |
| Loss                | -130     |
| Real Det Return     | -772     |
| Real Sto Return     | -332     |
| Running Env Steps   | 1625000  |
| Running Forward KL  | 30.4     |
| Running Reverse KL  | 3.57     |
| Running Update Time | 325      |
----------------------------------
-2024-05-13 08:11:17.497436 ʱ-
| Itration            | 326      |
| Loss                | -202     |
| Real Det Return     | -874     |
| Real Sto Return     | -360     |
| Running Env Steps   | 1630000  |
| Running Forward KL  | 31.2     |
| Running Reverse KL  | 3.27     |
| Running Update Time | 326      |
----------------------------------
-2024-05-13 08:13:42.152112 ʱ-
| Itration            | 327      |
| Loss                | -165     |
| Real Det Return     | -773     |
| Real Sto Return     | -296     |
| Running Env Steps   | 1635000  |
| Running Forward KL  | 30.2     |
| Running Reverse KL  | 3.48     |
| Running Update Time | 327      |
----------------------------------
-2024-05-13 08:16:07.033934 ʱ-
| Itration            | 328      |
| Loss                | -157     |
| Real Det Return     | -835     |
| Real Sto Return     | -361     |
| Running Env Steps   | 1640000  |
| Running Forward KL  | 30.4     |
| Running Reverse KL  | 3.3      |
| Running Update Time | 328      |
----------------------------------
-2024-05-13 08:18:32.422891 ʱ-
| Itration            | 329      |
| Loss                | -186     |
| Real Det Return     | -578     |
| Real Sto Return     | -297     |
| Running Env Steps   | 1645000  |
| Running Forward KL  | 31.3     |
| Running Reverse KL  | 3.4      |
| Running Update Time | 329      |
----------------------------------
-2024-05-13 08:20:57.439311 ʱ-
| Itration            | 330      |
| Loss                | -176     |
| Real Det Return     | -879     |
| Real Sto Return     | -336     |
| Running Env Steps   | 1650000  |
| Running Forward KL  | 30.5     |
| Running Reverse KL  | 3.33     |
| Running Update Time | 330      |
----------------------------------
-2024-05-13 08:23:22.455456 ʱ-
| Itration            | 331      |
| Loss                | -168     |
| Real Det Return     | -938     |
| Real Sto Return     | -348     |
| Running Env Steps   | 1655000  |
| Running Forward KL  | 30.4     |
| Running Reverse KL  | 3.61     |
| Running Update Time | 331      |
----------------------------------
-2024-05-13 08:25:47.120526 ʱ-
| Itration            | 332      |
| Loss                | -154     |
| Real Det Return     | -686     |
| Real Sto Return     | -344     |
| Running Env Steps   | 1660000  |
| Running Forward KL  | 30.5     |
| Running Reverse KL  | 3.47     |
| Running Update Time | 332      |
----------------------------------
-2024-05-13 08:28:11.791182 ʱ-
| Itration            | 333      |
| Loss                | -211     |
| Real Det Return     | -532     |
| Real Sto Return     | -279     |
| Running Env Steps   | 1665000  |
| Running Forward KL  | 29.7     |
| Running Reverse KL  | 3.04     |
| Running Update Time | 333      |
----------------------------------
-2024-05-13 08:30:38.673718 ʱ-
| Itration            | 334      |
| Loss                | -178     |
| Real Det Return     | -709     |
| Real Sto Return     | -311     |
| Running Env Steps   | 1670000  |
| Running Forward KL  | 30.1     |
| Running Reverse KL  | 3.34     |
| Running Update Time | 334      |
----------------------------------
-2024-05-13 08:33:04.023072 ʱ-
| Itration            | 335      |
| Loss                | -137     |
| Real Det Return     | -861     |
| Real Sto Return     | -336     |
| Running Env Steps   | 1675000  |
| Running Forward KL  | 29.6     |
| Running Reverse KL  | 3.09     |
| Running Update Time | 335      |
----------------------------------
-2024-05-13 08:35:29.227761 ʱ-
| Itration            | 336      |
| Loss                | -157     |
| Real Det Return     | -552     |
| Real Sto Return     | -320     |
| Running Env Steps   | 1680000  |
| Running Forward KL  | 29.4     |
| Running Reverse KL  | 3.4      |
| Running Update Time | 336      |
----------------------------------
-2024-05-13 08:37:54.469026 ʱ-
| Itration            | 337      |
| Loss                | -155     |
| Real Det Return     | -643     |
| Real Sto Return     | -305     |
| Running Env Steps   | 1685000  |
| Running Forward KL  | 29.9     |
| Running Reverse KL  | 3.23     |
| Running Update Time | 337      |
----------------------------------
-2024-05-13 08:40:19.802076 ʱ-
| Itration            | 338      |
| Loss                | -163     |
| Real Det Return     | -641     |
| Real Sto Return     | -315     |
| Running Env Steps   | 1690000  |
| Running Forward KL  | 29.9     |
| Running Reverse KL  | 3.26     |
| Running Update Time | 338      |
----------------------------------
-2024-05-13 08:42:44.717707 ʱ-
| Itration            | 339      |
| Loss                | -205     |
| Real Det Return     | -965     |
| Real Sto Return     | -316     |
| Running Env Steps   | 1695000  |
| Running Forward KL  | 31       |
| Running Reverse KL  | 3.27     |
| Running Update Time | 339      |
----------------------------------
-2024-05-13 08:45:09.812846 ʱ-
| Itration            | 340      |
| Loss                | -198     |
| Real Det Return     | -497     |
| Real Sto Return     | -297     |
| Running Env Steps   | 1700000  |
| Running Forward KL  | 30.2     |
| Running Reverse KL  | 3.16     |
| Running Update Time | 340      |
----------------------------------
-2024-05-13 08:47:34.856425 ʱ-
| Itration            | 341      |
| Loss                | -200     |
| Real Det Return     | -685     |
| Real Sto Return     | -321     |
| Running Env Steps   | 1705000  |
| Running Forward KL  | 30.7     |
| Running Reverse KL  | 3.36     |
| Running Update Time | 341      |
----------------------------------
-2024-05-13 08:50:00.000594 ʱ-
| Itration            | 342      |
| Loss                | -210     |
| Real Det Return     | -756     |
| Real Sto Return     | -275     |
| Running Env Steps   | 1710000  |
| Running Forward KL  | 30.2     |
| Running Reverse KL  | 3.31     |
| Running Update Time | 342      |
----------------------------------
-2024-05-13 08:52:25.283798 ʱ-
| Itration            | 343      |
| Loss                | -171     |
| Real Det Return     | -143     |
| Real Sto Return     | -314     |
| Running Env Steps   | 1715000  |
| Running Forward KL  | 30.1     |
| Running Reverse KL  | 3.69     |
| Running Update Time | 343      |
----------------------------------
-2024-05-13 08:54:50.688855 ʱ-
| Itration            | 344      |
| Loss                | -195     |
| Real Det Return     | -793     |
| Real Sto Return     | -286     |
| Running Env Steps   | 1720000  |
| Running Forward KL  | 29.2     |
| Running Reverse KL  | 3.04     |
| Running Update Time | 344      |
----------------------------------
-2024-05-13 08:57:15.933882 ʱ-
| Itration            | 345      |
| Loss                | -211     |
| Real Det Return     | -912     |
| Real Sto Return     | -337     |
| Running Env Steps   | 1725000  |
| Running Forward KL  | 30.1     |
| Running Reverse KL  | 3.41     |
| Running Update Time | 345      |
----------------------------------
-2024-05-13 08:59:41.311352 ʱ-
| Itration            | 346      |
| Loss                | -172     |
| Real Det Return     | -611     |
| Real Sto Return     | -289     |
| Running Env Steps   | 1730000  |
| Running Forward KL  | 29.1     |
| Running Reverse KL  | 3.12     |
| Running Update Time | 346      |
----------------------------------
-2024-05-13 09:02:06.472506 ʱ-
| Itration            | 347      |
| Loss                | -175     |
| Real Det Return     | -359     |
| Real Sto Return     | -266     |
| Running Env Steps   | 1735000  |
| Running Forward KL  | 29.6     |
| Running Reverse KL  | 3.55     |
| Running Update Time | 347      |
----------------------------------
-2024-05-13 09:04:31.554355 ʱ-
| Itration            | 348      |
| Loss                | -167     |
| Real Det Return     | -964     |
| Real Sto Return     | -358     |
| Running Env Steps   | 1740000  |
| Running Forward KL  | 30.2     |
| Running Reverse KL  | 3.23     |
| Running Update Time | 348      |
----------------------------------
-2024-05-13 09:06:56.966278 ʱ-
| Itration            | 349      |
| Loss                | -190     |
| Real Det Return     | -665     |
| Real Sto Return     | -341     |
| Running Env Steps   | 1745000  |
| Running Forward KL  | 30.2     |
| Running Reverse KL  | 3.19     |
| Running Update Time | 349      |
----------------------------------
-2024-05-13 09:09:22.356165 ʱ-
| Itration            | 350      |
| Loss                | -183     |
| Real Det Return     | -741     |
| Real Sto Return     | -296     |
| Running Env Steps   | 1750000  |
| Running Forward KL  | 30       |
| Running Reverse KL  | 3.35     |
| Running Update Time | 350      |
----------------------------------
-2024-05-13 09:11:47.677879 ʱ-
| Itration            | 351      |
| Loss                | -176     |
| Real Det Return     | -803     |
| Real Sto Return     | -305     |
| Running Env Steps   | 1755000  |
| Running Forward KL  | 29.6     |
| Running Reverse KL  | 3.13     |
| Running Update Time | 351      |
----------------------------------
-2024-05-13 09:14:13.348585 ʱ-
| Itration            | 352      |
| Loss                | -163     |
| Real Det Return     | -908     |
| Real Sto Return     | -374     |
| Running Env Steps   | 1760000  |
| Running Forward KL  | 29.5     |
| Running Reverse KL  | 3.24     |
| Running Update Time | 352      |
----------------------------------
-2024-05-13 09:16:39.271320 ʱ-
| Itration            | 353      |
| Loss                | -186     |
| Real Det Return     | -689     |
| Real Sto Return     | -279     |
| Running Env Steps   | 1765000  |
| Running Forward KL  | 29.6     |
| Running Reverse KL  | 3.26     |
| Running Update Time | 353      |
----------------------------------
-2024-05-13 09:19:05.144611 ʱ-
| Itration            | 354      |
| Loss                | -206     |
| Real Det Return     | -642     |
| Real Sto Return     | -295     |
| Running Env Steps   | 1770000  |
| Running Forward KL  | 29.5     |
| Running Reverse KL  | 2.98     |
| Running Update Time | 354      |
----------------------------------
-2024-05-13 09:21:30.814968 ʱ-
| Itration            | 355      |
| Loss                | -188     |
| Real Det Return     | -740     |
| Real Sto Return     | -328     |
| Running Env Steps   | 1775000  |
| Running Forward KL  | 30.1     |
| Running Reverse KL  | 3.42     |
| Running Update Time | 355      |
----------------------------------
-2024-05-13 09:23:56.869501 ʱ-
| Itration            | 356      |
| Loss                | -208     |
| Real Det Return     | -892     |
| Real Sto Return     | -347     |
| Running Env Steps   | 1780000  |
| Running Forward KL  | 29.3     |
| Running Reverse KL  | 3.15     |
| Running Update Time | 356      |
----------------------------------
-2024-05-13 09:26:22.583854 ʱ-
| Itration            | 357      |
| Loss                | -194     |
| Real Det Return     | -905     |
| Real Sto Return     | -328     |
| Running Env Steps   | 1785000  |
| Running Forward KL  | 30       |
| Running Reverse KL  | 3.44     |
| Running Update Time | 357      |
----------------------------------
-2024-05-13 09:28:48.245918 ʱ-
| Itration            | 358      |
| Loss                | -200     |
| Real Det Return     | -674     |
| Real Sto Return     | -295     |
| Running Env Steps   | 1790000  |
| Running Forward KL  | 29.8     |
| Running Reverse KL  | 3.58     |
| Running Update Time | 358      |
----------------------------------
-2024-05-13 09:31:14.409814 ʱ-
| Itration            | 359      |
| Loss                | -187     |
| Real Det Return     | -526     |
| Real Sto Return     | -266     |
| Running Env Steps   | 1795000  |
| Running Forward KL  | 29.9     |
| Running Reverse KL  | 3.42     |
| Running Update Time | 359      |
----------------------------------
-2024-05-13 09:33:40.261384 ʱ-
| Itration            | 360      |
| Loss                | -230     |
| Real Det Return     | -425     |
| Real Sto Return     | -252     |
| Running Env Steps   | 1800000  |
| Running Forward KL  | 29.2     |
| Running Reverse KL  | 3.16     |
| Running Update Time | 360      |
----------------------------------
-2024-05-13 09:36:05.784203 ʱ-
| Itration            | 361      |
| Loss                | -172     |
| Real Det Return     | -623     |
| Real Sto Return     | -312     |
| Running Env Steps   | 1805000  |
| Running Forward KL  | 30       |
| Running Reverse KL  | 3.46     |
| Running Update Time | 361      |
----------------------------------
-2024-05-13 09:38:31.110110 ʱ-
| Itration            | 362      |
| Loss                | -197     |
| Real Det Return     | -712     |
| Real Sto Return     | -307     |
| Running Env Steps   | 1810000  |
| Running Forward KL  | 29.8     |
| Running Reverse KL  | 3.09     |
| Running Update Time | 362      |
----------------------------------
-2024-05-13 09:40:56.980510 ʱ-
| Itration            | 363      |
| Loss                | -161     |
| Real Det Return     | -677     |
| Real Sto Return     | -311     |
| Running Env Steps   | 1815000  |
| Running Forward KL  | 29.2     |
| Running Reverse KL  | 3.41     |
| Running Update Time | 363      |
----------------------------------
-2024-05-13 09:43:22.822949 ʱ-
| Itration            | 364      |
| Loss                | -171     |
| Real Det Return     | -495     |
| Real Sto Return     | -291     |
| Running Env Steps   | 1820000  |
| Running Forward KL  | 29.9     |
| Running Reverse KL  | 3.38     |
| Running Update Time | 364      |
----------------------------------
-2024-05-13 09:45:48.666342 ʱ-
| Itration            | 365      |
| Loss                | -194     |
| Real Det Return     | -869     |
| Real Sto Return     | -329     |
| Running Env Steps   | 1825000  |
| Running Forward KL  | 28.9     |
| Running Reverse KL  | 2.93     |
| Running Update Time | 365      |
----------------------------------
-2024-05-13 09:48:14.606228 ʱ-
| Itration            | 366      |
| Loss                | -192     |
| Real Det Return     | -496     |
| Real Sto Return     | -246     |
| Running Env Steps   | 1830000  |
| Running Forward KL  | 29.3     |
| Running Reverse KL  | 3.3      |
| Running Update Time | 366      |
----------------------------------
-2024-05-13 09:50:40.896432 ʱ-
| Itration            | 367      |
| Loss                | -192     |
| Real Det Return     | -812     |
| Real Sto Return     | -333     |
| Running Env Steps   | 1835000  |
| Running Forward KL  | 29       |
| Running Reverse KL  | 3.16     |
| Running Update Time | 367      |
----------------------------------
-2024-05-13 09:53:07.052783 ʱ-
| Itration            | 368      |
| Loss                | -173     |
| Real Det Return     | -841     |
| Real Sto Return     | -375     |
| Running Env Steps   | 1840000  |
| Running Forward KL  | 29.4     |
| Running Reverse KL  | 3.63     |
| Running Update Time | 368      |
----------------------------------
-2024-05-13 09:55:32.955474 ʱ-
| Itration            | 369      |
| Loss                | -190     |
| Real Det Return     | -313     |
| Real Sto Return     | -256     |
| Running Env Steps   | 1845000  |
| Running Forward KL  | 29.4     |
| Running Reverse KL  | 3.74     |
| Running Update Time | 369      |
----------------------------------
-2024-05-13 09:57:58.923351 ʱ-
| Itration            | 370      |
| Loss                | -181     |
| Real Det Return     | -744     |
| Real Sto Return     | -312     |
| Running Env Steps   | 1850000  |
| Running Forward KL  | 28.4     |
| Running Reverse KL  | 3.42     |
| Running Update Time | 370      |
----------------------------------
-2024-05-13 10:00:24.976336 ʱ-
| Itration            | 371      |
| Loss                | -205     |
| Real Det Return     | -690     |
| Real Sto Return     | -283     |
| Running Env Steps   | 1855000  |
| Running Forward KL  | 29.5     |
| Running Reverse KL  | 3.44     |
| Running Update Time | 371      |
----------------------------------
-2024-05-13 10:02:50.904355 ʱ-
| Itration            | 372      |
| Loss                | -155     |
| Real Det Return     | -456     |
| Real Sto Return     | -259     |
| Running Env Steps   | 1860000  |
| Running Forward KL  | 29.1     |
| Running Reverse KL  | 3.29     |
| Running Update Time | 372      |
----------------------------------
-2024-05-13 10:05:17.015791 ʱ-
| Itration            | 373      |
| Loss                | -173     |
| Real Det Return     | -744     |
| Real Sto Return     | -379     |
| Running Env Steps   | 1865000  |
| Running Forward KL  | 29.5     |
| Running Reverse KL  | 3.54     |
| Running Update Time | 373      |
----------------------------------
-2024-05-13 10:07:42.931964 ʱ-
| Itration            | 374      |
| Loss                | -158     |
| Real Det Return     | -607     |
| Real Sto Return     | -287     |
| Running Env Steps   | 1870000  |
| Running Forward KL  | 28.8     |
| Running Reverse KL  | 3.62     |
| Running Update Time | 374      |
----------------------------------
-2024-05-13 10:10:09.164842 ʱ-
| Itration            | 375      |
| Loss                | -181     |
| Real Det Return     | -677     |
| Real Sto Return     | -357     |
| Running Env Steps   | 1875000  |
| Running Forward KL  | 28.2     |
| Running Reverse KL  | 2.95     |
| Running Update Time | 375      |
----------------------------------
-2024-05-13 10:12:35.257466 ʱ-
| Itration            | 376      |
| Loss                | -203     |
| Real Det Return     | -631     |
| Real Sto Return     | -303     |
| Running Env Steps   | 1880000  |
| Running Forward KL  | 29.9     |
| Running Reverse KL  | 3.64     |
| Running Update Time | 376      |
----------------------------------
-2024-05-13 10:15:01.340886 ʱ-
| Itration            | 377      |
| Loss                | -160     |
| Real Det Return     | -414     |
| Real Sto Return     | -265     |
| Running Env Steps   | 1885000  |
| Running Forward KL  | 29.1     |
| Running Reverse KL  | 3.18     |
| Running Update Time | 377      |
----------------------------------
-2024-05-13 10:17:27.468760 ʱ-
| Itration            | 378      |
| Loss                | -149     |
| Real Det Return     | -398     |
| Real Sto Return     | -253     |
| Running Env Steps   | 1890000  |
| Running Forward KL  | 28.9     |
| Running Reverse KL  | 3.33     |
| Running Update Time | 378      |
----------------------------------
-2024-05-13 10:19:53.687152 ʱ-
| Itration            | 379      |
| Loss                | -171     |
| Real Det Return     | -472     |
| Real Sto Return     | -249     |
| Running Env Steps   | 1895000  |
| Running Forward KL  | 29.3     |
| Running Reverse KL  | 3.42     |
| Running Update Time | 379      |
----------------------------------
-2024-05-13 10:22:19.779402 ʱ-
| Itration            | 380      |
| Loss                | -146     |
| Real Det Return     | -682     |
| Real Sto Return     | -306     |
| Running Env Steps   | 1900000  |
| Running Forward KL  | 29.4     |
| Running Reverse KL  | 3.59     |
| Running Update Time | 380      |
----------------------------------
-2024-05-13 10:24:46.143492 ʱ-
| Itration            | 381      |
| Loss                | -200     |
| Real Det Return     | -749     |
| Real Sto Return     | -356     |
| Running Env Steps   | 1905000  |
| Running Forward KL  | 29.3     |
| Running Reverse KL  | 3.15     |
| Running Update Time | 381      |
----------------------------------
-2024-05-13 10:27:12.251940 ʱ-
| Itration            | 382      |
| Loss                | -164     |
| Real Det Return     | -706     |
| Real Sto Return     | -316     |
| Running Env Steps   | 1910000  |
| Running Forward KL  | 29.6     |
| Running Reverse KL  | 3.48     |
| Running Update Time | 382      |
----------------------------------
-2024-05-13 10:29:38.570763 ʱ-
| Itration            | 383      |
| Loss                | -178     |
| Real Det Return     | -635     |
| Real Sto Return     | -320     |
| Running Env Steps   | 1915000  |
| Running Forward KL  | 29.1     |
| Running Reverse KL  | 3.5      |
| Running Update Time | 383      |
----------------------------------
-2024-05-13 10:32:04.777502 ʱ-
| Itration            | 384      |
| Loss                | -192     |
| Real Det Return     | -643     |
| Real Sto Return     | -281     |
| Running Env Steps   | 1920000  |
| Running Forward KL  | 28.8     |
| Running Reverse KL  | 3.11     |
| Running Update Time | 384      |
----------------------------------
-2024-05-13 10:34:31.199421 ʱ-
| Itration            | 385      |
| Loss                | -179     |
| Real Det Return     | -398     |
| Real Sto Return     | -256     |
| Running Env Steps   | 1925000  |
| Running Forward KL  | 29       |
| Running Reverse KL  | 3.63     |
| Running Update Time | 385      |
----------------------------------
-2024-05-13 10:36:57.587192 ʱ-
| Itration            | 386      |
| Loss                | -161     |
| Real Det Return     | -587     |
| Real Sto Return     | -272     |
| Running Env Steps   | 1930000  |
| Running Forward KL  | 29.2     |
| Running Reverse KL  | 3.41     |
| Running Update Time | 386      |
----------------------------------
-2024-05-13 10:39:23.842590 ʱ-
| Itration            | 387      |
| Loss                | -215     |
| Real Det Return     | -208     |
| Real Sto Return     | -266     |
| Running Env Steps   | 1935000  |
| Running Forward KL  | 28.7     |
| Running Reverse KL  | 3.14     |
| Running Update Time | 387      |
----------------------------------
-2024-05-13 10:41:50.216360 ʱ-
| Itration            | 388      |
| Loss                | -178     |
| Real Det Return     | -497     |
| Real Sto Return     | -283     |
| Running Env Steps   | 1940000  |
| Running Forward KL  | 28.9     |
| Running Reverse KL  | 3.47     |
| Running Update Time | 388      |
----------------------------------
-2024-05-13 10:44:16.279402 ʱ-
| Itration            | 389      |
| Loss                | -223     |
| Real Det Return     | -443     |
| Real Sto Return     | -257     |
| Running Env Steps   | 1945000  |
| Running Forward KL  | 28.7     |
| Running Reverse KL  | 3.25     |
| Running Update Time | 389      |
----------------------------------
-2024-05-13 10:46:42.802240 ʱ-
| Itration            | 390      |
| Loss                | -228     |
| Real Det Return     | -372     |
| Real Sto Return     | -268     |
| Running Env Steps   | 1950000  |
| Running Forward KL  | 29.5     |
| Running Reverse KL  | 3.37     |
| Running Update Time | 390      |
----------------------------------
-2024-05-13 10:49:09.496571 ʱ-
| Itration            | 391      |
| Loss                | -233     |
| Real Det Return     | -554     |
| Real Sto Return     | -278     |
| Running Env Steps   | 1955000  |
| Running Forward KL  | 29.2     |
| Running Reverse KL  | 3.24     |
| Running Update Time | 391      |
----------------------------------
-2024-05-13 10:51:36.389346 ʱ-
| Itration            | 392      |
| Loss                | -189     |
| Real Det Return     | -447     |
| Real Sto Return     | -291     |
| Running Env Steps   | 1960000  |
| Running Forward KL  | 28.3     |
| Running Reverse KL  | 3.23     |
| Running Update Time | 392      |
----------------------------------
-2024-05-13 10:54:03.082632 ʱ-
| Itration            | 393      |
| Loss                | -213     |
| Real Det Return     | -597     |
| Real Sto Return     | -279     |
| Running Env Steps   | 1965000  |
| Running Forward KL  | 29.1     |
| Running Reverse KL  | 3.46     |
| Running Update Time | 393      |
----------------------------------
-2024-05-13 10:56:30.026019 ʱ-
| Itration            | 394      |
| Loss                | -199     |
| Real Det Return     | -473     |
| Real Sto Return     | -266     |
| Running Env Steps   | 1970000  |
| Running Forward KL  | 28.6     |
| Running Reverse KL  | 3.36     |
| Running Update Time | 394      |
----------------------------------
-2024-05-13 10:58:56.405830 ʱ-
| Itration            | 395      |
| Loss                | -178     |
| Real Det Return     | -797     |
| Real Sto Return     | -352     |
| Running Env Steps   | 1975000  |
| Running Forward KL  | 28.7     |
| Running Reverse KL  | 3.09     |
| Running Update Time | 395      |
----------------------------------
-2024-05-13 11:01:23.207432 ʱ-
| Itration            | 396      |
| Loss                | -197     |
| Real Det Return     | -468     |
| Real Sto Return     | -267     |
| Running Env Steps   | 1980000  |
| Running Forward KL  | 29       |
| Running Reverse KL  | 3.52     |
| Running Update Time | 396      |
----------------------------------
-2024-05-13 11:03:49.924270 ʱ-
| Itration            | 397      |
| Loss                | -181     |
| Real Det Return     | -549     |
| Real Sto Return     | -272     |
| Running Env Steps   | 1985000  |
| Running Forward KL  | 29.4     |
| Running Reverse KL  | 3.75     |
| Running Update Time | 397      |
----------------------------------
-2024-05-13 11:06:17.084765 ʱ-
| Itration            | 398      |
| Loss                | -214     |
| Real Det Return     | -404     |
| Real Sto Return     | -281     |
| Running Env Steps   | 1990000  |
| Running Forward KL  | 28.9     |
| Running Reverse KL  | 3.6      |
| Running Update Time | 398      |
----------------------------------
-2024-05-13 11:08:43.666556 ʱ-
| Itration            | 399      |
| Loss                | -187     |
| Real Det Return     | -681     |
| Real Sto Return     | -275     |
| Running Env Steps   | 1995000  |
| Running Forward KL  | 28.8     |
| Running Reverse KL  | 3.21     |
| Running Update Time | 399      |
----------------------------------
-2024-05-13 11:11:10.554605 ʱ-
| Itration            | 400      |
| Loss                | -240     |
| Real Det Return     | -628     |
| Real Sto Return     | -293     |
| Running Env Steps   | 2000000  |
| Running Forward KL  | 28.8     |
| Running Reverse KL  | 3.45     |
| Running Update Time | 400      |
----------------------------------
-2024-05-13 11:13:37.995417 ʱ-
| Itration            | 401      |
| Loss                | -169     |
| Real Det Return     | -514     |
| Real Sto Return     | -260     |
| Running Env Steps   | 2005000  |
| Running Forward KL  | 28.2     |
| Running Reverse KL  | 3.56     |
| Running Update Time | 401      |
----------------------------------
-2024-05-13 11:16:04.936193 ʱ-
| Itration            | 402      |
| Loss                | -213     |
| Real Det Return     | -398     |
| Real Sto Return     | -280     |
| Running Env Steps   | 2010000  |
| Running Forward KL  | 27.9     |
| Running Reverse KL  | 3.21     |
| Running Update Time | 402      |
----------------------------------
-2024-05-13 11:18:32.272095 ʱ-
| Itration            | 403      |
| Loss                | -185     |
| Real Det Return     | -442     |
| Real Sto Return     | -258     |
| Running Env Steps   | 2015000  |
| Running Forward KL  | 29.2     |
| Running Reverse KL  | 3.81     |
| Running Update Time | 403      |
----------------------------------
-2024-05-13 11:20:59.303369 ʱ-
| Itration            | 404      |
| Loss                | -234     |
| Real Det Return     | -662     |
| Real Sto Return     | -265     |
| Running Env Steps   | 2020000  |
| Running Forward KL  | 28.3     |
| Running Reverse KL  | 3.2      |
| Running Update Time | 404      |
----------------------------------
-2024-05-13 11:23:26.371574 ʱ-
| Itration            | 405      |
| Loss                | -208     |
| Real Det Return     | -592     |
| Real Sto Return     | -267     |
| Running Env Steps   | 2025000  |
| Running Forward KL  | 28.9     |
| Running Reverse KL  | 3.42     |
| Running Update Time | 405      |
----------------------------------
-2024-05-13 11:25:53.398133 ʱ-
| Itration            | 406      |
| Loss                | -209     |
| Real Det Return     | -179     |
| Real Sto Return     | -238     |
| Running Env Steps   | 2030000  |
| Running Forward KL  | 27.7     |
| Running Reverse KL  | 3.48     |
| Running Update Time | 406      |
----------------------------------
-2024-05-13 11:28:22.219810 ʱ-
| Itration            | 407      |
| Loss                | -207     |
| Real Det Return     | -613     |
| Real Sto Return     | -318     |
| Running Env Steps   | 2035000  |
| Running Forward KL  | 29.1     |
| Running Reverse KL  | 3.53     |
| Running Update Time | 407      |
----------------------------------
-2024-05-13 11:30:49.942968 ʱ-
| Itration            | 408      |
| Loss                | -212     |
| Real Det Return     | -741     |
| Real Sto Return     | -279     |
| Running Env Steps   | 2040000  |
| Running Forward KL  | 28.2     |
| Running Reverse KL  | 3.58     |
| Running Update Time | 408      |
----------------------------------
-2024-05-13 11:33:17.699604 ʱ-
| Itration            | 409      |
| Loss                | -212     |
| Real Det Return     | -431     |
| Real Sto Return     | -248     |
| Running Env Steps   | 2045000  |
| Running Forward KL  | 28.4     |
| Running Reverse KL  | 3.24     |
| Running Update Time | 409      |
----------------------------------
-2024-05-13 11:35:44.853424 ʱ-
| Itration            | 410      |
| Loss                | -214     |
| Real Det Return     | -504     |
| Real Sto Return     | -257     |
| Running Env Steps   | 2050000  |
| Running Forward KL  | 28.6     |
| Running Reverse KL  | 3.67     |
| Running Update Time | 410      |
----------------------------------
-2024-05-13 11:38:11.977564 ʱ-
| Itration            | 411      |
| Loss                | -216     |
| Real Det Return     | -564     |
| Real Sto Return     | -353     |
| Running Env Steps   | 2055000  |
| Running Forward KL  | 29.2     |
| Running Reverse KL  | 3.66     |
| Running Update Time | 411      |
----------------------------------
-2024-05-13 11:40:39.101638 ʱ-
| Itration            | 412      |
| Loss                | -182     |
| Real Det Return     | -532     |
| Real Sto Return     | -275     |
| Running Env Steps   | 2060000  |
| Running Forward KL  | 29       |
| Running Reverse KL  | 3.79     |
| Running Update Time | 412      |
----------------------------------
-2024-05-13 11:43:05.585186 ʱ-
| Itration            | 413      |
| Loss                | -198     |
| Real Det Return     | -492     |
| Real Sto Return     | -242     |
| Running Env Steps   | 2065000  |
| Running Forward KL  | 28.3     |
| Running Reverse KL  | 3.72     |
| Running Update Time | 413      |
----------------------------------
-2024-05-13 11:45:32.792594 ʱ-
| Itration            | 414      |
| Loss                | -193     |
| Real Det Return     | -663     |
| Real Sto Return     | -349     |
| Running Env Steps   | 2070000  |
| Running Forward KL  | 29.3     |
| Running Reverse KL  | 3.88     |
| Running Update Time | 414      |
----------------------------------
-2024-05-13 11:47:59.796653 ʱ-
| Itration            | 415      |
| Loss                | -195     |
| Real Det Return     | -635     |
| Real Sto Return     | -281     |
| Running Env Steps   | 2075000  |
| Running Forward KL  | 28.6     |
| Running Reverse KL  | 3.81     |
| Running Update Time | 415      |
----------------------------------
-2024-05-13 11:50:27.036211 ʱ-
| Itration            | 416      |
| Loss                | -213     |
| Real Det Return     | -573     |
| Real Sto Return     | -284     |
| Running Env Steps   | 2080000  |
| Running Forward KL  | 28.4     |
| Running Reverse KL  | 3.16     |
| Running Update Time | 416      |
----------------------------------
-2024-05-13 11:52:54.196434 ʱ-
| Itration            | 417      |
| Loss                | -195     |
| Real Det Return     | -546     |
| Real Sto Return     | -252     |
| Running Env Steps   | 2085000  |
| Running Forward KL  | 27.9     |
| Running Reverse KL  | 3.53     |
| Running Update Time | 417      |
----------------------------------
-2024-05-13 11:55:21.709500 ʱ-
| Itration            | 418      |
| Loss                | -214     |
| Real Det Return     | -757     |
| Real Sto Return     | -298     |
| Running Env Steps   | 2090000  |
| Running Forward KL  | 28.6     |
| Running Reverse KL  | 3.38     |
| Running Update Time | 418      |
----------------------------------
-2024-05-13 11:57:49.339098 ʱ-
| Itration            | 419      |
| Loss                | -227     |
| Real Det Return     | -458     |
| Real Sto Return     | -265     |
| Running Env Steps   | 2095000  |
| Running Forward KL  | 28.2     |
| Running Reverse KL  | 3.15     |
| Running Update Time | 419      |
----------------------------------
-2024-05-13 12:00:16.937684 ʱ-
| Itration            | 420      |
| Loss                | -200     |
| Real Det Return     | -483     |
| Real Sto Return     | -237     |
| Running Env Steps   | 2100000  |
| Running Forward KL  | 28.2     |
| Running Reverse KL  | 3.73     |
| Running Update Time | 420      |
----------------------------------
-2024-05-13 12:02:43.951951 ʱ-
| Itration            | 421      |
| Loss                | -166     |
| Real Det Return     | -490     |
| Real Sto Return     | -257     |
| Running Env Steps   | 2105000  |
| Running Forward KL  | 28.3     |
| Running Reverse KL  | 3.45     |
| Running Update Time | 421      |
----------------------------------
-2024-05-13 12:05:11.516707 ʱ-
| Itration            | 422      |
| Loss                | -205     |
| Real Det Return     | -251     |
| Real Sto Return     | -238     |
| Running Env Steps   | 2110000  |
| Running Forward KL  | 27.7     |
| Running Reverse KL  | 3.27     |
| Running Update Time | 422      |
----------------------------------
-2024-05-13 12:07:38.487977 ʱ-
| Itration            | 423      |
| Loss                | -232     |
| Real Det Return     | -415     |
| Real Sto Return     | -240     |
| Running Env Steps   | 2115000  |
| Running Forward KL  | 28.4     |
| Running Reverse KL  | 3.56     |
| Running Update Time | 423      |
----------------------------------
-2024-05-13 12:10:05.478508 ʱ-
| Itration            | 424      |
| Loss                | -238     |
| Real Det Return     | -264     |
| Real Sto Return     | -249     |
| Running Env Steps   | 2120000  |
| Running Forward KL  | 28.4     |
| Running Reverse KL  | 3.64     |
| Running Update Time | 424      |
----------------------------------
-2024-05-13 12:12:32.866435 ʱ-
| Itration            | 425      |
| Loss                | -198     |
| Real Det Return     | -123     |
| Real Sto Return     | -257     |
| Running Env Steps   | 2125000  |
| Running Forward KL  | 27.8     |
| Running Reverse KL  | 3.73     |
| Running Update Time | 425      |
----------------------------------
-2024-05-13 12:15:00.224871 ʱ-
| Itration            | 426      |
| Loss                | -201     |
| Real Det Return     | -644     |
| Real Sto Return     | -280     |
| Running Env Steps   | 2130000  |
| Running Forward KL  | 28.3     |
| Running Reverse KL  | 3.66     |
| Running Update Time | 426      |
----------------------------------
-2024-05-13 12:17:28.194754 ʱ-
| Itration            | 427      |
| Loss                | -186     |
| Real Det Return     | -243     |
| Real Sto Return     | -227     |
| Running Env Steps   | 2135000  |
| Running Forward KL  | 28.2     |
| Running Reverse KL  | 3.53     |
| Running Update Time | 427      |
----------------------------------
-2024-05-13 12:19:55.266063 ʱ-
| Itration            | 428      |
| Loss                | -200     |
| Real Det Return     | -619     |
| Real Sto Return     | -268     |
| Running Env Steps   | 2140000  |
| Running Forward KL  | 28.4     |
| Running Reverse KL  | 3.6      |
| Running Update Time | 428      |
----------------------------------
-2024-05-13 12:22:22.347291 ʱ-
| Itration            | 429      |
| Loss                | -243     |
| Real Det Return     | -626     |
| Real Sto Return     | -278     |
| Running Env Steps   | 2145000  |
| Running Forward KL  | 28.2     |
| Running Reverse KL  | 3.74     |
| Running Update Time | 429      |
----------------------------------
-2024-05-13 12:24:49.637650 ʱ-
| Itration            | 430      |
| Loss                | -216     |
| Real Det Return     | -569     |
| Real Sto Return     | -269     |
| Running Env Steps   | 2150000  |
| Running Forward KL  | 28       |
| Running Reverse KL  | 3.44     |
| Running Update Time | 430      |
----------------------------------
-2024-05-13 12:27:17.013437 ʱ-
| Itration            | 431      |
| Loss                | -224     |
| Real Det Return     | -415     |
| Real Sto Return     | -239     |
| Running Env Steps   | 2155000  |
| Running Forward KL  | 27.8     |
| Running Reverse KL  | 3.33     |
| Running Update Time | 431      |
----------------------------------
-2024-05-13 12:29:44.449039 ʱ-
| Itration            | 432      |
| Loss                | -206     |
| Real Det Return     | -636     |
| Real Sto Return     | -261     |
| Running Env Steps   | 2160000  |
| Running Forward KL  | 28.6     |
| Running Reverse KL  | 3.57     |
| Running Update Time | 432      |
----------------------------------
-2024-05-13 12:32:11.974410 ʱ-
| Itration            | 433      |
| Loss                | -257     |
| Real Det Return     | -579     |
| Real Sto Return     | -263     |
| Running Env Steps   | 2165000  |
| Running Forward KL  | 27.6     |
| Running Reverse KL  | 3.16     |
| Running Update Time | 433      |
----------------------------------
-2024-05-13 12:34:39.150441 ʱ-
| Itration            | 434      |
| Loss                | -186     |
| Real Det Return     | -277     |
| Real Sto Return     | -224     |
| Running Env Steps   | 2170000  |
| Running Forward KL  | 27.6     |
| Running Reverse KL  | 3.93     |
| Running Update Time | 434      |
----------------------------------
-2024-05-13 12:37:06.797621 ʱ-
| Itration            | 435      |
| Loss                | -213     |
| Real Det Return     | -466     |
| Real Sto Return     | -281     |
| Running Env Steps   | 2175000  |
| Running Forward KL  | 28.6     |
| Running Reverse KL  | 3.83     |
| Running Update Time | 435      |
----------------------------------
-2024-05-13 12:39:34.053430 ʱ-
| Itration            | 436      |
| Loss                | -214     |
| Real Det Return     | -419     |
| Real Sto Return     | -236     |
| Running Env Steps   | 2180000  |
| Running Forward KL  | 28.1     |
| Running Reverse KL  | 3.73     |
| Running Update Time | 436      |
----------------------------------
-2024-05-13 12:42:01.466638 ʱ-
| Itration            | 437      |
| Loss                | -228     |
| Real Det Return     | -517     |
| Real Sto Return     | -303     |
| Running Env Steps   | 2185000  |
| Running Forward KL  | 28.2     |
| Running Reverse KL  | 3.57     |
| Running Update Time | 437      |
----------------------------------
-2024-05-13 12:44:29.005799 ʱ-
| Itration            | 438      |
| Loss                | -267     |
| Real Det Return     | -239     |
| Real Sto Return     | -227     |
| Running Env Steps   | 2190000  |
| Running Forward KL  | 27.1     |
| Running Reverse KL  | 3.23     |
| Running Update Time | 438      |
----------------------------------
-2024-05-13 12:46:56.425904 ʱ-
| Itration            | 439      |
| Loss                | -231     |
| Real Det Return     | -566     |
| Real Sto Return     | -254     |
| Running Env Steps   | 2195000  |
| Running Forward KL  | 27.9     |
| Running Reverse KL  | 3.53     |
| Running Update Time | 439      |
----------------------------------
-2024-05-13 12:49:24.048146 ʱ-
| Itration            | 440      |
| Loss                | -184     |
| Real Det Return     | -386     |
| Real Sto Return     | -223     |
| Running Env Steps   | 2200000  |
| Running Forward KL  | 27.4     |
| Running Reverse KL  | 3.87     |
| Running Update Time | 440      |
----------------------------------
-2024-05-13 12:51:51.603045 ʱ-
| Itration            | 441      |
| Loss                | -199     |
| Real Det Return     | -408     |
| Real Sto Return     | -271     |
| Running Env Steps   | 2205000  |
| Running Forward KL  | 27.4     |
| Running Reverse KL  | 3.03     |
| Running Update Time | 441      |
----------------------------------
-2024-05-13 12:54:19.517456 ʱ-
| Itration            | 442      |
| Loss                | -201     |
| Real Det Return     | -592     |
| Real Sto Return     | -248     |
| Running Env Steps   | 2210000  |
| Running Forward KL  | 27.4     |
| Running Reverse KL  | 3.27     |
| Running Update Time | 442      |
----------------------------------
-2024-05-13 12:56:46.895046 ʱ-
| Itration            | 443      |
| Loss                | -215     |
| Real Det Return     | -480     |
| Real Sto Return     | -251     |
| Running Env Steps   | 2215000  |
| Running Forward KL  | 27.8     |
| Running Reverse KL  | 3.66     |
| Running Update Time | 443      |
----------------------------------
-2024-05-13 12:59:14.050162 ʱ-
| Itration            | 444      |
| Loss                | -174     |
| Real Det Return     | -198     |
| Real Sto Return     | -225     |
| Running Env Steps   | 2220000  |
| Running Forward KL  | 27.6     |
| Running Reverse KL  | 3.67     |
| Running Update Time | 444      |
----------------------------------
-2024-05-13 13:01:41.939180 ʱ-
| Itration            | 445      |
| Loss                | -237     |
| Real Det Return     | -271     |
| Real Sto Return     | -260     |
| Running Env Steps   | 2225000  |
| Running Forward KL  | 28.4     |
| Running Reverse KL  | 3.76     |
| Running Update Time | 445      |
----------------------------------
-2024-05-13 13:04:09.982228 ʱ-
| Itration            | 446      |
| Loss                | -223     |
| Real Det Return     | -416     |
| Real Sto Return     | -244     |
| Running Env Steps   | 2230000  |
| Running Forward KL  | 27.5     |
| Running Reverse KL  | 3.69     |
| Running Update Time | 446      |
----------------------------------
-2024-05-13 13:06:38.458583 ʱ-
| Itration            | 447      |
| Loss                | -227     |
| Real Det Return     | -184     |
| Real Sto Return     | -239     |
| Running Env Steps   | 2235000  |
| Running Forward KL  | 28.2     |
| Running Reverse KL  | 3.64     |
| Running Update Time | 447      |
----------------------------------
-2024-05-13 13:09:06.838887 ʱ-
| Itration            | 448      |
| Loss                | -237     |
| Real Det Return     | -315     |
| Real Sto Return     | -232     |
| Running Env Steps   | 2240000  |
| Running Forward KL  | 27.8     |
| Running Reverse KL  | 3.65     |
| Running Update Time | 448      |
----------------------------------
-2024-05-13 13:11:43.936383 ʱ-
| Itration            | 449      |
| Loss                | -231     |
| Real Det Return     | -385     |
| Real Sto Return     | -254     |
| Running Env Steps   | 2245000  |
| Running Forward KL  | 28.1     |
| Running Reverse KL  | 3.41     |
| Running Update Time | 449      |
----------------------------------
-2024-05-13 13:14:17.959147 ʱ-
| Itration            | 450      |
| Loss                | -202     |
| Real Det Return     | -495     |
| Real Sto Return     | -299     |
| Running Env Steps   | 2250000  |
| Running Forward KL  | 28.2     |
| Running Reverse KL  | 3.99     |
| Running Update Time | 450      |
----------------------------------
-2024-05-13 13:16:51.143971 ʱ-
| Itration            | 451      |
| Loss                | -267     |
| Real Det Return     | -386     |
| Real Sto Return     | -234     |
| Running Env Steps   | 2255000  |
| Running Forward KL  | 27.7     |
| Running Reverse KL  | 3.63     |
| Running Update Time | 451      |
----------------------------------
-2024-05-13 13:19:26.845203 ʱ-
| Itration            | 452      |
| Loss                | -207     |
| Real Det Return     | -516     |
| Real Sto Return     | -261     |
| Running Env Steps   | 2260000  |
| Running Forward KL  | 28.1     |
| Running Reverse KL  | 4.06     |
| Running Update Time | 452      |
----------------------------------
-2024-05-13 13:22:02.681478 ʱ-
| Itration            | 453      |
| Loss                | -230     |
| Real Det Return     | -381     |
| Real Sto Return     | -224     |
| Running Env Steps   | 2265000  |
| Running Forward KL  | 27       |
| Running Reverse KL  | 3.72     |
| Running Update Time | 453      |
----------------------------------
-2024-05-13 13:24:37.850991 ʱ-
| Itration            | 454      |
| Loss                | -215     |
| Real Det Return     | -242     |
| Real Sto Return     | -236     |
| Running Env Steps   | 2270000  |
| Running Forward KL  | 27.2     |
| Running Reverse KL  | 3.64     |
| Running Update Time | 454      |
----------------------------------
-2024-05-13 13:27:09.849654 ʱ-
| Itration            | 455      |
| Loss                | -194     |
| Real Det Return     | -669     |
| Real Sto Return     | -272     |
| Running Env Steps   | 2275000  |
| Running Forward KL  | 27.8     |
| Running Reverse KL  | 3.37     |
| Running Update Time | 455      |
----------------------------------
-2024-05-13 13:29:43.624770 ʱ-
| Itration            | 456      |
| Loss                | -205     |
| Real Det Return     | -473     |
| Real Sto Return     | -268     |
| Running Env Steps   | 2280000  |
| Running Forward KL  | 27.4     |
| Running Reverse KL  | 3.14     |
| Running Update Time | 456      |
----------------------------------
-2024-05-13 13:32:15.729193 ʱ-
| Itration            | 457      |
| Loss                | -233     |
| Real Det Return     | -479     |
| Real Sto Return     | -236     |
| Running Env Steps   | 2285000  |
| Running Forward KL  | 27.3     |
| Running Reverse KL  | 3.34     |
| Running Update Time | 457      |
----------------------------------
-2024-05-13 13:34:49.534029 ʱ-
| Itration            | 458      |
| Loss                | -231     |
| Real Det Return     | -452     |
| Real Sto Return     | -223     |
| Running Env Steps   | 2290000  |
| Running Forward KL  | 27.8     |
| Running Reverse KL  | 3.64     |
| Running Update Time | 458      |
----------------------------------
-2024-05-13 13:37:22.233010 ʱ-
| Itration            | 459      |
| Loss                | -208     |
| Real Det Return     | -535     |
| Real Sto Return     | -249     |
| Running Env Steps   | 2295000  |
| Running Forward KL  | 27.6     |
| Running Reverse KL  | 3.43     |
| Running Update Time | 459      |
----------------------------------
-2024-05-13 13:39:58.303039 ʱ-
| Itration            | 460      |
| Loss                | -221     |
| Real Det Return     | -444     |
| Real Sto Return     | -243     |
| Running Env Steps   | 2300000  |
| Running Forward KL  | 28.1     |
| Running Reverse KL  | 3.78     |
| Running Update Time | 460      |
----------------------------------
-2024-05-13 13:42:33.031272 ʱ-
| Itration            | 461      |
| Loss                | -218     |
| Real Det Return     | -688     |
| Real Sto Return     | -277     |
| Running Env Steps   | 2305000  |
| Running Forward KL  | 27.8     |
| Running Reverse KL  | 3.64     |
| Running Update Time | 461      |
----------------------------------
-2024-05-13 13:45:07.866040 ʱ-
| Itration            | 462      |
| Loss                | -221     |
| Real Det Return     | -514     |
| Real Sto Return     | -261     |
| Running Env Steps   | 2310000  |
| Running Forward KL  | 26.9     |
| Running Reverse KL  | 3.26     |
| Running Update Time | 462      |
----------------------------------
-2024-05-13 13:47:42.414242 ʱ-
| Itration            | 463      |
| Loss                | -209     |
| Real Det Return     | -316     |
| Real Sto Return     | -249     |
| Running Env Steps   | 2315000  |
| Running Forward KL  | 28       |
| Running Reverse KL  | 3.48     |
| Running Update Time | 463      |
----------------------------------
-2024-05-13 13:50:21.269741 ʱ-
| Itration            | 464      |
| Loss                | -245     |
| Real Det Return     | -707     |
| Real Sto Return     | -345     |
| Running Env Steps   | 2320000  |
| Running Forward KL  | 27.4     |
| Running Reverse KL  | 3.74     |
| Running Update Time | 464      |
----------------------------------
-2024-05-13 13:52:59.369767 ʱ-
| Itration            | 465      |
| Loss                | -256     |
| Real Det Return     | -265     |
| Real Sto Return     | -223     |
| Running Env Steps   | 2325000  |
| Running Forward KL  | 27       |
| Running Reverse KL  | 3.36     |
| Running Update Time | 465      |
----------------------------------
-2024-05-13 13:55:36.141658 ʱ-
| Itration            | 466      |
| Loss                | -192     |
| Real Det Return     | -336     |
| Real Sto Return     | -232     |
| Running Env Steps   | 2330000  |
| Running Forward KL  | 27.2     |
| Running Reverse KL  | 3.68     |
| Running Update Time | 466      |
----------------------------------
-2024-05-13 13:58:16.135624 ʱ-
| Itration            | 467      |
| Loss                | -199     |
| Real Det Return     | -433     |
| Real Sto Return     | -234     |
| Running Env Steps   | 2335000  |
| Running Forward KL  | 27.5     |
| Running Reverse KL  | 3.9      |
| Running Update Time | 467      |
----------------------------------
-2024-05-13 14:00:55.965826 ʱ-
| Itration            | 468      |
| Loss                | -251     |
| Real Det Return     | -362     |
| Real Sto Return     | -239     |
| Running Env Steps   | 2340000  |
| Running Forward KL  | 27.7     |
| Running Reverse KL  | 4.06     |
| Running Update Time | 468      |
----------------------------------
-2024-05-13 14:03:34.848704 ʱ-
| Itration            | 469      |
| Loss                | -266     |
| Real Det Return     | -221     |
| Real Sto Return     | -211     |
| Running Env Steps   | 2345000  |
| Running Forward KL  | 27.2     |
| Running Reverse KL  | 3.55     |
| Running Update Time | 469      |
----------------------------------
-2024-05-13 14:06:01.072459 ʱ-
| Itration            | 470      |
| Loss                | -233     |
| Real Det Return     | -343     |
| Real Sto Return     | -239     |
| Running Env Steps   | 2350000  |
| Running Forward KL  | 27.4     |
| Running Reverse KL  | 4.16     |
| Running Update Time | 470      |
----------------------------------
-2024-05-13 14:08:27.360672 ʱ-
| Itration            | 471      |
| Loss                | -235     |
| Real Det Return     | -572     |
| Real Sto Return     | -254     |
| Running Env Steps   | 2355000  |
| Running Forward KL  | 27.2     |
| Running Reverse KL  | 3.54     |
| Running Update Time | 471      |
----------------------------------
-2024-05-13 14:10:54.289739 ʱ-
| Itration            | 472      |
| Loss                | -218     |
| Real Det Return     | -471     |
| Real Sto Return     | -271     |
| Running Env Steps   | 2360000  |
| Running Forward KL  | 27.2     |
| Running Reverse KL  | 3.88     |
| Running Update Time | 472      |
----------------------------------
-2024-05-13 14:13:22.831713 ʱ-
| Itration            | 473      |
| Loss                | -218     |
| Real Det Return     | -383     |
| Real Sto Return     | -235     |
| Running Env Steps   | 2365000  |
| Running Forward KL  | 27.5     |
| Running Reverse KL  | 3.7      |
| Running Update Time | 473      |
----------------------------------
-2024-05-13 14:15:45.963026 ʱ-
| Itration            | 474      |
| Loss                | -216     |
| Real Det Return     | -261     |
| Real Sto Return     | -227     |
| Running Env Steps   | 2370000  |
| Running Forward KL  | 26.8     |
| Running Reverse KL  | 3.56     |
| Running Update Time | 474      |
----------------------------------
-2024-05-13 14:18:12.802432 ʱ-
| Itration            | 475      |
| Loss                | -188     |
| Real Det Return     | -332     |
| Real Sto Return     | -237     |
| Running Env Steps   | 2375000  |
| Running Forward KL  | 26.9     |
| Running Reverse KL  | 3.96     |
| Running Update Time | 475      |
----------------------------------
-2024-05-13 14:20:38.540219 ʱ-
| Itration            | 476      |
| Loss                | -226     |
| Real Det Return     | -331     |
| Real Sto Return     | -224     |
| Running Env Steps   | 2380000  |
| Running Forward KL  | 27.4     |
| Running Reverse KL  | 4.15     |
| Running Update Time | 476      |
----------------------------------
-2024-05-13 14:23:05.184319 ʱ-
| Itration            | 477      |
| Loss                | -232     |
| Real Det Return     | -348     |
| Real Sto Return     | -274     |
| Running Env Steps   | 2385000  |
| Running Forward KL  | 27.7     |
| Running Reverse KL  | 3.71     |
| Running Update Time | 477      |
----------------------------------
-2024-05-13 14:25:30.532983 ʱ-
| Itration            | 478      |
| Loss                | -241     |
| Real Det Return     | -468     |
| Real Sto Return     | -261     |
| Running Env Steps   | 2390000  |
| Running Forward KL  | 27.9     |
| Running Reverse KL  | 3.7      |
| Running Update Time | 478      |
----------------------------------
-2024-05-13 14:27:56.432081 ʱ-
| Itration            | 479      |
| Loss                | -244     |
| Real Det Return     | -251     |
| Real Sto Return     | -296     |
| Running Env Steps   | 2395000  |
| Running Forward KL  | 27.5     |
| Running Reverse KL  | 3.58     |
| Running Update Time | 479      |
----------------------------------
-2024-05-13 14:30:22.527527 ʱ-
| Itration            | 480      |
| Loss                | -236     |
| Real Det Return     | -294     |
| Real Sto Return     | -243     |
| Running Env Steps   | 2400000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 3.45     |
| Running Update Time | 480      |
----------------------------------
-2024-05-13 14:32:49.586770 ʱ-
| Itration            | 481      |
| Loss                | -216     |
| Real Det Return     | -81.8    |
| Real Sto Return     | -251     |
| Running Env Steps   | 2405000  |
| Running Forward KL  | 27.1     |
| Running Reverse KL  | 3.73     |
| Running Update Time | 481      |
----------------------------------
-2024-05-13 14:35:16.284427 ʱ-
| Itration            | 482      |
| Loss                | -229     |
| Real Det Return     | -343     |
| Real Sto Return     | -249     |
| Running Env Steps   | 2410000  |
| Running Forward KL  | 27.1     |
| Running Reverse KL  | 3.5      |
| Running Update Time | 482      |
----------------------------------
-2024-05-13 14:37:43.616552 ʱ-
| Itration            | 483      |
| Loss                | -222     |
| Real Det Return     | -436     |
| Real Sto Return     | -272     |
| Running Env Steps   | 2415000  |
| Running Forward KL  | 27.3     |
| Running Reverse KL  | 3.71     |
| Running Update Time | 483      |
----------------------------------
-2024-05-13 14:40:09.710146 ʱ-
| Itration            | 484      |
| Loss                | -187     |
| Real Det Return     | -261     |
| Real Sto Return     | -231     |
| Running Env Steps   | 2420000  |
| Running Forward KL  | 26.4     |
| Running Reverse KL  | 3.93     |
| Running Update Time | 484      |
----------------------------------
-2024-05-13 14:42:35.026621 ʱ-
| Itration            | 485      |
| Loss                | -222     |
| Real Det Return     | -560     |
| Real Sto Return     | -263     |
| Running Env Steps   | 2425000  |
| Running Forward KL  | 26.8     |
| Running Reverse KL  | 3.77     |
| Running Update Time | 485      |
----------------------------------
-2024-05-13 14:45:01.295999 ʱ-
| Itration            | 486      |
| Loss                | -237     |
| Real Det Return     | -326     |
| Real Sto Return     | -211     |
| Running Env Steps   | 2430000  |
| Running Forward KL  | 27.3     |
| Running Reverse KL  | 4        |
| Running Update Time | 486      |
----------------------------------
-2024-05-13 14:47:27.696401 ʱ-
| Itration            | 487      |
| Loss                | -212     |
| Real Det Return     | -223     |
| Real Sto Return     | -231     |
| Running Env Steps   | 2435000  |
| Running Forward KL  | 26.7     |
| Running Reverse KL  | 3.42     |
| Running Update Time | 487      |
----------------------------------
-2024-05-13 14:49:54.218742 ʱ-
| Itration            | 488      |
| Loss                | -255     |
| Real Det Return     | -380     |
| Real Sto Return     | -244     |
| Running Env Steps   | 2440000  |
| Running Forward KL  | 27.2     |
| Running Reverse KL  | 3.81     |
| Running Update Time | 488      |
----------------------------------
-2024-05-13 14:52:20.505534 ʱ-
| Itration            | 489      |
| Loss                | -263     |
| Real Det Return     | -287     |
| Real Sto Return     | -217     |
| Running Env Steps   | 2445000  |
| Running Forward KL  | 26.5     |
| Running Reverse KL  | 3.27     |
| Running Update Time | 489      |
----------------------------------
-2024-05-13 14:54:46.949013 ʱ-
| Itration            | 490      |
| Loss                | -224     |
| Real Det Return     | -627     |
| Real Sto Return     | -274     |
| Running Env Steps   | 2450000  |
| Running Forward KL  | 26.5     |
| Running Reverse KL  | 3.42     |
| Running Update Time | 490      |
----------------------------------
-2024-05-13 14:57:13.852460 ʱ-
| Itration            | 491      |
| Loss                | -268     |
| Real Det Return     | -629     |
| Real Sto Return     | -236     |
| Running Env Steps   | 2455000  |
| Running Forward KL  | 27.4     |
| Running Reverse KL  | 3.46     |
| Running Update Time | 491      |
----------------------------------
-2024-05-13 14:59:40.455124 ʱ-
| Itration            | 492      |
| Loss                | -221     |
| Real Det Return     | -243     |
| Real Sto Return     | -220     |
| Running Env Steps   | 2460000  |
| Running Forward KL  | 27.5     |
| Running Reverse KL  | 4.31     |
| Running Update Time | 492      |
----------------------------------
-2024-05-13 15:02:06.700032 ʱ-
| Itration            | 493      |
| Loss                | -212     |
| Real Det Return     | -151     |
| Real Sto Return     | -214     |
| Running Env Steps   | 2465000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 3.88     |
| Running Update Time | 493      |
----------------------------------
-2024-05-13 15:04:33.500673 ʱ-
| Itration            | 494      |
| Loss                | -224     |
| Real Det Return     | -438     |
| Real Sto Return     | -262     |
| Running Env Steps   | 2470000  |
| Running Forward KL  | 27.3     |
| Running Reverse KL  | 4.05     |
| Running Update Time | 494      |
----------------------------------
-2024-05-13 15:06:59.929712 ʱ-
| Itration            | 495      |
| Loss                | -238     |
| Real Det Return     | -795     |
| Real Sto Return     | -312     |
| Running Env Steps   | 2475000  |
| Running Forward KL  | 26.9     |
| Running Reverse KL  | 3.96     |
| Running Update Time | 495      |
----------------------------------
-2024-05-13 15:09:27.366907 ʱ-
| Itration            | 496      |
| Loss                | -259     |
| Real Det Return     | -370     |
| Real Sto Return     | -212     |
| Running Env Steps   | 2480000  |
| Running Forward KL  | 26.8     |
| Running Reverse KL  | 3.69     |
| Running Update Time | 496      |
----------------------------------
-2024-05-13 15:11:53.181409 ʱ-
| Itration            | 497      |
| Loss                | -223     |
| Real Det Return     | -518     |
| Real Sto Return     | -271     |
| Running Env Steps   | 2485000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 3.35     |
| Running Update Time | 497      |
----------------------------------
-2024-05-13 15:14:20.161980 ʱ-
| Itration            | 498      |
| Loss                | -251     |
| Real Det Return     | -219     |
| Real Sto Return     | -216     |
| Running Env Steps   | 2490000  |
| Running Forward KL  | 25.8     |
| Running Reverse KL  | 3.35     |
| Running Update Time | 498      |
----------------------------------
-2024-05-13 15:16:46.642215 ʱ-
| Itration            | 499      |
| Loss                | -262     |
| Real Det Return     | -114     |
| Real Sto Return     | -229     |
| Running Env Steps   | 2495000  |
| Running Forward KL  | 26.5     |
| Running Reverse KL  | 3.89     |
| Running Update Time | 499      |
----------------------------------
-2024-05-13 15:19:14.268820 ʱ-
| Itration            | 500      |
| Loss                | -256     |
| Real Det Return     | -333     |
| Real Sto Return     | -225     |
| Running Env Steps   | 2500000  |
| Running Forward KL  | 27.1     |
| Running Reverse KL  | 3.89     |
| Running Update Time | 500      |
----------------------------------
-2024-05-13 15:21:41.455146 ʱ-
| Itration            | 501      |
| Loss                | -261     |
| Real Det Return     | -215     |
| Real Sto Return     | -244     |
| Running Env Steps   | 2505000  |
| Running Forward KL  | 26.9     |
| Running Reverse KL  | 3.53     |
| Running Update Time | 501      |
----------------------------------
-2024-05-13 15:24:09.370681 ʱ-
| Itration            | 502      |
| Loss                | -246     |
| Real Det Return     | -306     |
| Real Sto Return     | -208     |
| Running Env Steps   | 2510000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 3.85     |
| Running Update Time | 502      |
----------------------------------
-2024-05-13 15:26:36.776497 ʱ-
| Itration            | 503      |
| Loss                | -249     |
| Real Det Return     | -719     |
| Real Sto Return     | -279     |
| Running Env Steps   | 2515000  |
| Running Forward KL  | 26.7     |
| Running Reverse KL  | 3.38     |
| Running Update Time | 503      |
----------------------------------
-2024-05-13 15:29:03.664978 ʱ-
| Itration            | 504      |
| Loss                | -246     |
| Real Det Return     | -370     |
| Real Sto Return     | -238     |
| Running Env Steps   | 2520000  |
| Running Forward KL  | 27.2     |
| Running Reverse KL  | 3.52     |
| Running Update Time | 504      |
----------------------------------
-2024-05-13 15:31:31.237677 ʱ-
| Itration            | 505      |
| Loss                | -262     |
| Real Det Return     | -212     |
| Real Sto Return     | -219     |
| Running Env Steps   | 2525000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 4.03     |
| Running Update Time | 505      |
----------------------------------
-2024-05-13 15:33:58.834123 ʱ-
| Itration            | 506      |
| Loss                | -266     |
| Real Det Return     | -259     |
| Real Sto Return     | -231     |
| Running Env Steps   | 2530000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 3.61     |
| Running Update Time | 506      |
----------------------------------
-2024-05-13 15:36:25.248441 ʱ-
| Itration            | 507      |
| Loss                | -284     |
| Real Det Return     | -642     |
| Real Sto Return     | -277     |
| Running Env Steps   | 2535000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 3.57     |
| Running Update Time | 507      |
----------------------------------
-2024-05-13 15:38:53.155471 ʱ-
| Itration            | 508      |
| Loss                | -252     |
| Real Det Return     | -576     |
| Real Sto Return     | -258     |
| Running Env Steps   | 2540000  |
| Running Forward KL  | 26.4     |
| Running Reverse KL  | 3.69     |
| Running Update Time | 508      |
----------------------------------
-2024-05-13 15:41:20.414038 ʱ-
| Itration            | 509      |
| Loss                | -240     |
| Real Det Return     | -194     |
| Real Sto Return     | -227     |
| Running Env Steps   | 2545000  |
| Running Forward KL  | 27       |
| Running Reverse KL  | 3.73     |
| Running Update Time | 509      |
----------------------------------
-2024-05-13 15:43:47.784051 ʱ-
| Itration            | 510      |
| Loss                | -277     |
| Real Det Return     | -498     |
| Real Sto Return     | -223     |
| Running Env Steps   | 2550000  |
| Running Forward KL  | 27.2     |
| Running Reverse KL  | 3.97     |
| Running Update Time | 510      |
----------------------------------
-2024-05-13 15:46:14.672077 ʱ-
| Itration            | 511      |
| Loss                | -251     |
| Real Det Return     | -195     |
| Real Sto Return     | -218     |
| Running Env Steps   | 2555000  |
| Running Forward KL  | 27.1     |
| Running Reverse KL  | 4.19     |
| Running Update Time | 511      |
----------------------------------
-2024-05-13 15:48:41.866209 ʱ-
| Itration            | 512      |
| Loss                | -251     |
| Real Det Return     | -409     |
| Real Sto Return     | -217     |
| Running Env Steps   | 2560000  |
| Running Forward KL  | 27       |
| Running Reverse KL  | 3.89     |
| Running Update Time | 512      |
----------------------------------
-2024-05-13 15:51:09.473698 ʱ-
| Itration            | 513      |
| Loss                | -225     |
| Real Det Return     | -133     |
| Real Sto Return     | -215     |
| Running Env Steps   | 2565000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 3.66     |
| Running Update Time | 513      |
----------------------------------
-2024-05-13 15:53:36.514463 ʱ-
| Itration            | 514      |
| Loss                | -235     |
| Real Det Return     | -256     |
| Real Sto Return     | -227     |
| Running Env Steps   | 2570000  |
| Running Forward KL  | 26.7     |
| Running Reverse KL  | 3.73     |
| Running Update Time | 514      |
----------------------------------
-2024-05-13 15:56:03.606633 ʱ-
| Itration            | 515      |
| Loss                | -262     |
| Real Det Return     | -596     |
| Real Sto Return     | -247     |
| Running Env Steps   | 2575000  |
| Running Forward KL  | 26.1     |
| Running Reverse KL  | 3.65     |
| Running Update Time | 515      |
----------------------------------
-2024-05-13 15:58:30.030532 ʱ-
| Itration            | 516      |
| Loss                | -252     |
| Real Det Return     | -266     |
| Real Sto Return     | -236     |
| Running Env Steps   | 2580000  |
| Running Forward KL  | 26.8     |
| Running Reverse KL  | 3.86     |
| Running Update Time | 516      |
----------------------------------
-2024-05-13 16:00:57.668729 ʱ-
| Itration            | 517      |
| Loss                | -245     |
| Real Det Return     | -604     |
| Real Sto Return     | -289     |
| Running Env Steps   | 2585000  |
| Running Forward KL  | 27.5     |
| Running Reverse KL  | 3.63     |
| Running Update Time | 517      |
----------------------------------
-2024-05-13 16:03:24.300879 ʱ-
| Itration            | 518      |
| Loss                | -283     |
| Real Det Return     | -81.6    |
| Real Sto Return     | -250     |
| Running Env Steps   | 2590000  |
| Running Forward KL  | 26.4     |
| Running Reverse KL  | 3.88     |
| Running Update Time | 518      |
----------------------------------
-2024-05-13 16:05:51.346600 ʱ-
| Itration            | 519      |
| Loss                | -263     |
| Real Det Return     | -602     |
| Real Sto Return     | -252     |
| Running Env Steps   | 2595000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 3.87     |
| Running Update Time | 519      |
----------------------------------
-2024-05-13 16:08:18.455442 ʱ-
| Itration            | 520      |
| Loss                | -256     |
| Real Det Return     | -254     |
| Real Sto Return     | -249     |
| Running Env Steps   | 2600000  |
| Running Forward KL  | 26.3     |
| Running Reverse KL  | 3.38     |
| Running Update Time | 520      |
----------------------------------
-2024-05-13 16:10:46.640246 ʱ-
| Itration            | 521      |
| Loss                | -253     |
| Real Det Return     | -804     |
| Real Sto Return     | -303     |
| Running Env Steps   | 2605000  |
| Running Forward KL  | 26.7     |
| Running Reverse KL  | 3.37     |
| Running Update Time | 521      |
----------------------------------
-2024-05-13 16:13:14.302617 ʱ-
| Itration            | 522      |
| Loss                | -301     |
| Real Det Return     | -434     |
| Real Sto Return     | -225     |
| Running Env Steps   | 2610000  |
| Running Forward KL  | 26.4     |
| Running Reverse KL  | 3.49     |
| Running Update Time | 522      |
----------------------------------
-2024-05-13 16:15:40.947763 ʱ-
| Itration            | 523      |
| Loss                | -243     |
| Real Det Return     | -627     |
| Real Sto Return     | -246     |
| Running Env Steps   | 2615000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 3.41     |
| Running Update Time | 523      |
----------------------------------
-2024-05-13 16:18:09.452228 ʱ-
| Itration            | 524      |
| Loss                | -240     |
| Real Det Return     | -713     |
| Real Sto Return     | -269     |
| Running Env Steps   | 2620000  |
| Running Forward KL  | 26.8     |
| Running Reverse KL  | 3.8      |
| Running Update Time | 524      |
----------------------------------
-2024-05-13 16:20:36.361036 ʱ-
| Itration            | 525      |
| Loss                | -272     |
| Real Det Return     | -211     |
| Real Sto Return     | -218     |
| Running Env Steps   | 2625000  |
| Running Forward KL  | 27.6     |
| Running Reverse KL  | 4.13     |
| Running Update Time | 525      |
----------------------------------
-2024-05-13 16:23:03.762809 ʱ-
| Itration            | 526      |
| Loss                | -258     |
| Real Det Return     | -543     |
| Real Sto Return     | -245     |
| Running Env Steps   | 2630000  |
| Running Forward KL  | 27       |
| Running Reverse KL  | 3.51     |
| Running Update Time | 526      |
----------------------------------
-2024-05-13 16:25:32.127082 ʱ-
| Itration            | 527      |
| Loss                | -236     |
| Real Det Return     | -613     |
| Real Sto Return     | -277     |
| Running Env Steps   | 2635000  |
| Running Forward KL  | 27.4     |
| Running Reverse KL  | 3.73     |
| Running Update Time | 527      |
----------------------------------
-2024-05-13 16:27:58.838163 ʱ-
| Itration            | 528      |
| Loss                | -233     |
| Real Det Return     | -425     |
| Real Sto Return     | -244     |
| Running Env Steps   | 2640000  |
| Running Forward KL  | 26.9     |
| Running Reverse KL  | 3.96     |
| Running Update Time | 528      |
----------------------------------
-2024-05-13 16:30:26.738704 ʱ-
| Itration            | 529      |
| Loss                | -240     |
| Real Det Return     | -694     |
| Real Sto Return     | -252     |
| Running Env Steps   | 2645000  |
| Running Forward KL  | 26.2     |
| Running Reverse KL  | 3.7      |
| Running Update Time | 529      |
----------------------------------
-2024-05-13 16:32:54.654889 ʱ-
| Itration            | 530      |
| Loss                | -266     |
| Real Det Return     | -256     |
| Real Sto Return     | -272     |
| Running Env Steps   | 2650000  |
| Running Forward KL  | 26.1     |
| Running Reverse KL  | 3.34     |
| Running Update Time | 530      |
----------------------------------
-2024-05-13 16:35:22.531335 ʱ-
| Itration            | 531      |
| Loss                | -280     |
| Real Det Return     | -355     |
| Real Sto Return     | -215     |
| Running Env Steps   | 2655000  |
| Running Forward KL  | 26.2     |
| Running Reverse KL  | 3.48     |
| Running Update Time | 531      |
----------------------------------
-2024-05-13 16:37:49.302686 ʱ-
| Itration            | 532      |
| Loss                | -286     |
| Real Det Return     | -150     |
| Real Sto Return     | -225     |
| Running Env Steps   | 2660000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 3.63     |
| Running Update Time | 532      |
----------------------------------
-2024-05-13 16:40:16.847327 ʱ-
| Itration            | 533      |
| Loss                | -272     |
| Real Det Return     | -546     |
| Real Sto Return     | -242     |
| Running Env Steps   | 2665000  |
| Running Forward KL  | 26.3     |
| Running Reverse KL  | 3.26     |
| Running Update Time | 533      |
----------------------------------
-2024-05-13 16:42:45.101983 ʱ-
| Itration            | 534      |
| Loss                | -283     |
| Real Det Return     | -407     |
| Real Sto Return     | -230     |
| Running Env Steps   | 2670000  |
| Running Forward KL  | 26.4     |
| Running Reverse KL  | 3.92     |
| Running Update Time | 534      |
----------------------------------
-2024-05-13 16:45:12.096301 ʱ-
| Itration            | 535      |
| Loss                | -311     |
| Real Det Return     | -497     |
| Real Sto Return     | -228     |
| Running Env Steps   | 2675000  |
| Running Forward KL  | 26.5     |
| Running Reverse KL  | 3.77     |
| Running Update Time | 535      |
----------------------------------
-2024-05-13 16:47:39.396291 ʱ-
| Itration            | 536      |
| Loss                | -273     |
| Real Det Return     | -355     |
| Real Sto Return     | -256     |
| Running Env Steps   | 2680000  |
| Running Forward KL  | 26.2     |
| Running Reverse KL  | 3.6      |
| Running Update Time | 536      |
----------------------------------
-2024-05-13 16:50:06.655968 ʱ-
| Itration            | 537      |
| Loss                | -262     |
| Real Det Return     | -314     |
| Real Sto Return     | -240     |
| Running Env Steps   | 2685000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 3.77     |
| Running Update Time | 537      |
----------------------------------
-2024-05-13 16:52:33.411651 ʱ-
| Itration            | 538      |
| Loss                | -263     |
| Real Det Return     | -502     |
| Real Sto Return     | -239     |
| Running Env Steps   | 2690000  |
| Running Forward KL  | 26       |
| Running Reverse KL  | 3.34     |
| Running Update Time | 538      |
----------------------------------
-2024-05-13 16:55:00.922290 ʱ-
| Itration            | 539      |
| Loss                | -273     |
| Real Det Return     | -714     |
| Real Sto Return     | -273     |
| Running Env Steps   | 2695000  |
| Running Forward KL  | 26.3     |
| Running Reverse KL  | 4.25     |
| Running Update Time | 539      |
----------------------------------
-2024-05-13 16:57:27.740296 ʱ-
| Itration            | 540      |
| Loss                | -254     |
| Real Det Return     | -486     |
| Real Sto Return     | -213     |
| Running Env Steps   | 2700000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 3.47     |
| Running Update Time | 540      |
----------------------------------
-2024-05-13 16:59:54.852292 ʱ-
| Itration            | 541      |
| Loss                | -309     |
| Real Det Return     | -567     |
| Real Sto Return     | -239     |
| Running Env Steps   | 2705000  |
| Running Forward KL  | 26.4     |
| Running Reverse KL  | 3.63     |
| Running Update Time | 541      |
----------------------------------
-2024-05-13 17:02:22.961594 ʱ-
| Itration            | 542      |
| Loss                | -290     |
| Real Det Return     | -398     |
| Real Sto Return     | -245     |
| Running Env Steps   | 2710000  |
| Running Forward KL  | 25.6     |
| Running Reverse KL  | 3.66     |
| Running Update Time | 542      |
----------------------------------
-2024-05-13 17:04:50.567919 ʱ-
| Itration            | 543      |
| Loss                | -318     |
| Real Det Return     | -547     |
| Real Sto Return     | -242     |
| Running Env Steps   | 2715000  |
| Running Forward KL  | 27.5     |
| Running Reverse KL  | 3.97     |
| Running Update Time | 543      |
----------------------------------
-2024-05-13 17:07:17.768185 ʱ-
| Itration            | 544      |
| Loss                | -278     |
| Real Det Return     | -570     |
| Real Sto Return     | -247     |
| Running Env Steps   | 2720000  |
| Running Forward KL  | 26.8     |
| Running Reverse KL  | 3.9      |
| Running Update Time | 544      |
----------------------------------
-2024-05-13 17:09:46.581225 ʱ-
| Itration            | 545      |
| Loss                | -246     |
| Real Det Return     | -673     |
| Real Sto Return     | -264     |
| Running Env Steps   | 2725000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 3.77     |
| Running Update Time | 545      |
----------------------------------
-2024-05-13 17:12:14.766318 ʱ-
| Itration            | 546      |
| Loss                | -239     |
| Real Det Return     | -167     |
| Real Sto Return     | -214     |
| Running Env Steps   | 2730000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 3.87     |
| Running Update Time | 546      |
----------------------------------
-2024-05-13 17:14:43.117581 ʱ-
| Itration            | 547      |
| Loss                | -287     |
| Real Det Return     | -261     |
| Real Sto Return     | -219     |
| Running Env Steps   | 2735000  |
| Running Forward KL  | 26.2     |
| Running Reverse KL  | 3.76     |
| Running Update Time | 547      |
----------------------------------
-2024-05-13 17:17:11.233132 ʱ-
| Itration            | 548      |
| Loss                | -275     |
| Real Det Return     | -607     |
| Real Sto Return     | -260     |
| Running Env Steps   | 2740000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 3.6      |
| Running Update Time | 548      |
----------------------------------
-2024-05-13 17:19:38.564857 ʱ-
| Itration            | 549      |
| Loss                | -223     |
| Real Det Return     | -436     |
| Real Sto Return     | -213     |
| Running Env Steps   | 2745000  |
| Running Forward KL  | 25.1     |
| Running Reverse KL  | 3.04     |
| Running Update Time | 549      |
----------------------------------
-2024-05-13 17:22:06.075318 ʱ-
| Itration            | 550      |
| Loss                | -280     |
| Real Det Return     | -333     |
| Real Sto Return     | -217     |
| Running Env Steps   | 2750000  |
| Running Forward KL  | 26.4     |
| Running Reverse KL  | 3.91     |
| Running Update Time | 550      |
----------------------------------
-2024-05-13 17:24:33.518120 ʱ-
| Itration            | 551      |
| Loss                | -289     |
| Real Det Return     | -592     |
| Real Sto Return     | -233     |
| Running Env Steps   | 2755000  |
| Running Forward KL  | 26.3     |
| Running Reverse KL  | 3.68     |
| Running Update Time | 551      |
----------------------------------
-2024-05-13 17:27:00.860387 ʱ-
| Itration            | 552      |
| Loss                | -239     |
| Real Det Return     | -639     |
| Real Sto Return     | -222     |
| Running Env Steps   | 2760000  |
| Running Forward KL  | 26.5     |
| Running Reverse KL  | 4.22     |
| Running Update Time | 552      |
----------------------------------
-2024-05-13 17:29:30.337763 ʱ-
| Itration            | 553      |
| Loss                | -284     |
| Real Det Return     | -232     |
| Real Sto Return     | -231     |
| Running Env Steps   | 2765000  |
| Running Forward KL  | 26.8     |
| Running Reverse KL  | 4.29     |
| Running Update Time | 553      |
----------------------------------
-2024-05-13 17:31:59.061415 ʱ-
| Itration            | 554      |
| Loss                | -284     |
| Real Det Return     | -353     |
| Real Sto Return     | -225     |
| Running Env Steps   | 2770000  |
| Running Forward KL  | 26.4     |
| Running Reverse KL  | 3.83     |
| Running Update Time | 554      |
----------------------------------
-2024-05-13 17:34:27.262356 ʱ-
| Itration            | 555      |
| Loss                | -263     |
| Real Det Return     | -261     |
| Real Sto Return     | -260     |
| Running Env Steps   | 2775000  |
| Running Forward KL  | 26.8     |
| Running Reverse KL  | 3.64     |
| Running Update Time | 555      |
----------------------------------
-2024-05-13 17:36:55.239413 ʱ-
| Itration            | 556      |
| Loss                | -265     |
| Real Det Return     | -200     |
| Real Sto Return     | -226     |
| Running Env Steps   | 2780000  |
| Running Forward KL  | 25.5     |
| Running Reverse KL  | 3.49     |
| Running Update Time | 556      |
----------------------------------
-2024-05-13 17:39:22.567963 ʱ-
| Itration            | 557      |
| Loss                | -274     |
| Real Det Return     | -801     |
| Real Sto Return     | -291     |
| Running Env Steps   | 2785000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 4.12     |
| Running Update Time | 557      |
----------------------------------
-2024-05-13 17:41:50.337999 ʱ-
| Itration            | 558      |
| Loss                | -272     |
| Real Det Return     | -303     |
| Real Sto Return     | -221     |
| Running Env Steps   | 2790000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 3.8      |
| Running Update Time | 558      |
----------------------------------
-2024-05-13 17:44:18.514097 ʱ-
| Itration            | 559      |
| Loss                | -270     |
| Real Det Return     | -96.8    |
| Real Sto Return     | -212     |
| Running Env Steps   | 2795000  |
| Running Forward KL  | 26.7     |
| Running Reverse KL  | 4.25     |
| Running Update Time | 559      |
----------------------------------
-2024-05-13 17:46:45.441142 ʱ-
| Itration            | 560      |
| Loss                | -271     |
| Real Det Return     | -531     |
| Real Sto Return     | -240     |
| Running Env Steps   | 2800000  |
| Running Forward KL  | 25.5     |
| Running Reverse KL  | 3.42     |
| Running Update Time | 560      |
----------------------------------
-2024-05-13 17:49:13.276835 ʱ-
| Itration            | 561      |
| Loss                | -307     |
| Real Det Return     | -222     |
| Real Sto Return     | -212     |
| Running Env Steps   | 2805000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 3.35     |
| Running Update Time | 561      |
----------------------------------
-2024-05-13 17:51:41.398070 ʱ-
| Itration            | 562      |
| Loss                | -288     |
| Real Det Return     | -124     |
| Real Sto Return     | -212     |
| Running Env Steps   | 2810000  |
| Running Forward KL  | 26.4     |
| Running Reverse KL  | 3.78     |
| Running Update Time | 562      |
----------------------------------
-2024-05-13 17:54:08.744891 ʱ-
| Itration            | 563      |
| Loss                | -309     |
| Real Det Return     | -128     |
| Real Sto Return     | -228     |
| Running Env Steps   | 2815000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 3.62     |
| Running Update Time | 563      |
----------------------------------
-2024-05-13 17:56:37.010450 ʱ-
| Itration            | 564      |
| Loss                | -260     |
| Real Det Return     | -328     |
| Real Sto Return     | -239     |
| Running Env Steps   | 2820000  |
| Running Forward KL  | 25.8     |
| Running Reverse KL  | 3.38     |
| Running Update Time | 564      |
----------------------------------
-2024-05-13 17:59:05.364862 ʱ-
| Itration            | 565      |
| Loss                | -268     |
| Real Det Return     | -460     |
| Real Sto Return     | -218     |
| Running Env Steps   | 2825000  |
| Running Forward KL  | 25.3     |
| Running Reverse KL  | 3.76     |
| Running Update Time | 565      |
----------------------------------
-2024-05-13 18:01:33.598842 ʱ-
| Itration            | 566      |
| Loss                | -293     |
| Real Det Return     | -255     |
| Real Sto Return     | -217     |
| Running Env Steps   | 2830000  |
| Running Forward KL  | 26.1     |
| Running Reverse KL  | 3.8      |
| Running Update Time | 566      |
----------------------------------
-2024-05-13 18:04:01.830318 ʱ-
| Itration            | 567      |
| Loss                | -282     |
| Real Det Return     | -634     |
| Real Sto Return     | -279     |
| Running Env Steps   | 2835000  |
| Running Forward KL  | 26.3     |
| Running Reverse KL  | 3.78     |
| Running Update Time | 567      |
----------------------------------
-2024-05-13 18:06:29.873055 ʱ-
| Itration            | 568      |
| Loss                | -291     |
| Real Det Return     | -335     |
| Real Sto Return     | -224     |
| Running Env Steps   | 2840000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 3.31     |
| Running Update Time | 568      |
----------------------------------
-2024-05-13 18:08:58.504350 ʱ-
| Itration            | 569      |
| Loss                | -294     |
| Real Det Return     | -253     |
| Real Sto Return     | -220     |
| Running Env Steps   | 2845000  |
| Running Forward KL  | 25.6     |
| Running Reverse KL  | 3.56     |
| Running Update Time | 569      |
----------------------------------
-2024-05-13 18:11:25.835944 ʱ-
| Itration            | 570      |
| Loss                | -303     |
| Real Det Return     | -466     |
| Real Sto Return     | -218     |
| Running Env Steps   | 2850000  |
| Running Forward KL  | 25.7     |
| Running Reverse KL  | 3.33     |
| Running Update Time | 570      |
----------------------------------
-2024-05-13 18:13:53.968248 ʱ-
| Itration            | 571      |
| Loss                | -278     |
| Real Det Return     | -666     |
| Real Sto Return     | -257     |
| Running Env Steps   | 2855000  |
| Running Forward KL  | 26.4     |
| Running Reverse KL  | 4.32     |
| Running Update Time | 571      |
----------------------------------
-2024-05-13 18:16:22.048660 ʱ-
| Itration            | 572      |
| Loss                | -286     |
| Real Det Return     | -538     |
| Real Sto Return     | -218     |
| Running Env Steps   | 2860000  |
| Running Forward KL  | 25.8     |
| Running Reverse KL  | 3.71     |
| Running Update Time | 572      |
----------------------------------
-2024-05-13 18:18:50.996166 ʱ-
| Itration            | 573      |
| Loss                | -302     |
| Real Det Return     | -733     |
| Real Sto Return     | -263     |
| Running Env Steps   | 2865000  |
| Running Forward KL  | 26.7     |
| Running Reverse KL  | 3.85     |
| Running Update Time | 573      |
----------------------------------
-2024-05-13 18:21:19.299573 ʱ-
| Itration            | 574      |
| Loss                | -309     |
| Real Det Return     | -428     |
| Real Sto Return     | -212     |
| Running Env Steps   | 2870000  |
| Running Forward KL  | 24.8     |
| Running Reverse KL  | 3.53     |
| Running Update Time | 574      |
----------------------------------
-2024-05-13 18:23:47.549981 ʱ-
| Itration            | 575      |
| Loss                | -269     |
| Real Det Return     | -203     |
| Real Sto Return     | -219     |
| Running Env Steps   | 2875000  |
| Running Forward KL  | 25.6     |
| Running Reverse KL  | 3.75     |
| Running Update Time | 575      |
----------------------------------
-2024-05-13 18:26:16.316879 ʱ-
| Itration            | 576      |
| Loss                | -297     |
| Real Det Return     | -690     |
| Real Sto Return     | -298     |
| Running Env Steps   | 2880000  |
| Running Forward KL  | 26.3     |
| Running Reverse KL  | 3.6      |
| Running Update Time | 576      |
----------------------------------
-2024-05-13 18:28:45.039758 ʱ-
| Itration            | 577      |
| Loss                | -276     |
| Real Det Return     | -561     |
| Real Sto Return     | -219     |
| Running Env Steps   | 2885000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 3.65     |
| Running Update Time | 577      |
----------------------------------
-2024-05-13 18:31:13.503632 ʱ-
| Itration            | 578      |
| Loss                | -299     |
| Real Det Return     | -151     |
| Real Sto Return     | -222     |
| Running Env Steps   | 2890000  |
| Running Forward KL  | 26.2     |
| Running Reverse KL  | 3.75     |
| Running Update Time | 578      |
----------------------------------
-2024-05-13 18:33:41.963106 ʱ-
| Itration            | 579      |
| Loss                | -286     |
| Real Det Return     | -438     |
| Real Sto Return     | -218     |
| Running Env Steps   | 2895000  |
| Running Forward KL  | 25.5     |
| Running Reverse KL  | 3.37     |
| Running Update Time | 579      |
----------------------------------
-2024-05-13 18:36:11.396560 ʱ-
| Itration            | 580      |
| Loss                | -253     |
| Real Det Return     | -414     |
| Real Sto Return     | -217     |
| Running Env Steps   | 2900000  |
| Running Forward KL  | 26.6     |
| Running Reverse KL  | 4.4      |
| Running Update Time | 580      |
----------------------------------
-2024-05-13 18:38:39.738257 ʱ-
| Itration            | 581      |
| Loss                | -251     |
| Real Det Return     | -670     |
| Real Sto Return     | -221     |
| Running Env Steps   | 2905000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 3.72     |
| Running Update Time | 581      |
----------------------------------
-2024-05-13 18:41:08.299295 ʱ-
| Itration            | 582      |
| Loss                | -336     |
| Real Det Return     | -597     |
| Real Sto Return     | -261     |
| Running Env Steps   | 2910000  |
| Running Forward KL  | 26.4     |
| Running Reverse KL  | 4.27     |
| Running Update Time | 582      |
----------------------------------
-2024-05-13 18:43:36.071690 ʱ-
| Itration            | 583      |
| Loss                | -273     |
| Real Det Return     | -355     |
| Real Sto Return     | -247     |
| Running Env Steps   | 2915000  |
| Running Forward KL  | 25.6     |
| Running Reverse KL  | 3.71     |
| Running Update Time | 583      |
----------------------------------
-2024-05-13 18:46:05.948672 ʱ-
| Itration            | 584      |
| Loss                | -275     |
| Real Det Return     | -558     |
| Real Sto Return     | -256     |
| Running Env Steps   | 2920000  |
| Running Forward KL  | 25.7     |
| Running Reverse KL  | 3.43     |
| Running Update Time | 584      |
----------------------------------
-2024-05-13 18:48:33.671480 ʱ-
| Itration            | 585      |
| Loss                | -311     |
| Real Det Return     | -438     |
| Real Sto Return     | -234     |
| Running Env Steps   | 2925000  |
| Running Forward KL  | 25.4     |
| Running Reverse KL  | 3.71     |
| Running Update Time | 585      |
----------------------------------
-2024-05-13 18:51:01.504003 ʱ-
| Itration            | 586      |
| Loss                | -311     |
| Real Det Return     | -302     |
| Real Sto Return     | -211     |
| Running Env Steps   | 2930000  |
| Running Forward KL  | 25.3     |
| Running Reverse KL  | 3.6      |
| Running Update Time | 586      |
----------------------------------
-2024-05-13 18:53:29.118495 ʱ-
| Itration            | 587      |
| Loss                | -280     |
| Real Det Return     | -196     |
| Real Sto Return     | -249     |
| Running Env Steps   | 2935000  |
| Running Forward KL  | 26       |
| Running Reverse KL  | 3.65     |
| Running Update Time | 587      |
----------------------------------
-2024-05-13 18:55:58.046313 ʱ-
| Itration            | 588      |
| Loss                | -295     |
| Real Det Return     | -755     |
| Real Sto Return     | -307     |
| Running Env Steps   | 2940000  |
| Running Forward KL  | 26.7     |
| Running Reverse KL  | 4.23     |
| Running Update Time | 588      |
----------------------------------
-2024-05-13 18:58:26.547643 ʱ-
| Itration            | 589      |
| Loss                | -313     |
| Real Det Return     | -376     |
| Real Sto Return     | -212     |
| Running Env Steps   | 2945000  |
| Running Forward KL  | 26.1     |
| Running Reverse KL  | 4.17     |
| Running Update Time | 589      |
----------------------------------
-2024-05-13 19:00:53.963269 ʱ-
| Itration            | 590      |
| Loss                | -271     |
| Real Det Return     | -213     |
| Real Sto Return     | -214     |
| Running Env Steps   | 2950000  |
| Running Forward KL  | 25.2     |
| Running Reverse KL  | 3.72     |
| Running Update Time | 590      |
----------------------------------
-2024-05-13 19:03:21.801193 ʱ-
| Itration            | 591      |
| Loss                | -261     |
| Real Det Return     | -600     |
| Real Sto Return     | -233     |
| Running Env Steps   | 2955000  |
| Running Forward KL  | 25.7     |
| Running Reverse KL  | 3.41     |
| Running Update Time | 591      |
----------------------------------
-2024-05-13 19:05:49.900719 ʱ-
| Itration            | 592      |
| Loss                | -328     |
| Real Det Return     | -124     |
| Real Sto Return     | -283     |
| Running Env Steps   | 2960000  |
| Running Forward KL  | 25.4     |
| Running Reverse KL  | 4.04     |
| Running Update Time | 592      |
----------------------------------
-2024-05-13 19:08:18.893421 ʱ-
| Itration            | 593      |
| Loss                | -310     |
| Real Det Return     | -517     |
| Real Sto Return     | -219     |
| Running Env Steps   | 2965000  |
| Running Forward KL  | 26.1     |
| Running Reverse KL  | 3.87     |
| Running Update Time | 593      |
----------------------------------
-2024-05-13 19:10:47.835938 ʱ-
| Itration            | 594      |
| Loss                | -305     |
| Real Det Return     | -317     |
| Real Sto Return     | -205     |
| Running Env Steps   | 2970000  |
| Running Forward KL  | 25.6     |
| Running Reverse KL  | 3.11     |
| Running Update Time | 594      |
----------------------------------
-2024-05-13 19:13:16.874545 ʱ-
| Itration            | 595      |
| Loss                | -317     |
| Real Det Return     | -258     |
| Real Sto Return     | -211     |
| Running Env Steps   | 2975000  |
| Running Forward KL  | 26.4     |
| Running Reverse KL  | 3.88     |
| Running Update Time | 595      |
----------------------------------
-2024-05-13 19:15:45.025807 ʱ-
| Itration            | 596      |
| Loss                | -335     |
| Real Det Return     | -210     |
| Real Sto Return     | -219     |
| Running Env Steps   | 2980000  |
| Running Forward KL  | 25.6     |
| Running Reverse KL  | 3.74     |
| Running Update Time | 596      |
----------------------------------
-2024-05-13 19:18:13.000026 ʱ-
| Itration            | 597      |
| Loss                | -292     |
| Real Det Return     | -186     |
| Real Sto Return     | -225     |
| Running Env Steps   | 2985000  |
| Running Forward KL  | 26.3     |
| Running Reverse KL  | 4        |
| Running Update Time | 597      |
----------------------------------
-2024-05-13 19:20:42.000786 ʱ-
| Itration            | 598      |
| Loss                | -298     |
| Real Det Return     | -311     |
| Real Sto Return     | -234     |
| Running Env Steps   | 2990000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 3.79     |
| Running Update Time | 598      |
----------------------------------
-2024-05-13 19:23:10.171715 ʱ-
| Itration            | 599      |
| Loss                | -293     |
| Real Det Return     | -250     |
| Real Sto Return     | -207     |
| Running Env Steps   | 2995000  |
| Running Forward KL  | 25.5     |
| Running Reverse KL  | 3.75     |
| Running Update Time | 599      |
----------------------------------
-2024-05-13 19:25:38.524896 ʱ-
| Itration            | 600      |
| Loss                | -292     |
| Real Det Return     | -357     |
| Real Sto Return     | -251     |
| Running Env Steps   | 3000000  |
| Running Forward KL  | 25.5     |
| Running Reverse KL  | 4.13     |
| Running Update Time | 600      |
----------------------------------
-2024-05-13 19:28:07.003043 ʱ-
| Itration            | 601      |
| Loss                | -259     |
| Real Det Return     | -395     |
| Real Sto Return     | -229     |
| Running Env Steps   | 3005000  |
| Running Forward KL  | 25.3     |
| Running Reverse KL  | 3.75     |
| Running Update Time | 601      |
----------------------------------
-2024-05-13 19:30:35.551683 ʱ-
| Itration            | 602      |
| Loss                | -309     |
| Real Det Return     | -497     |
| Real Sto Return     | -277     |
| Running Env Steps   | 3010000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 3.63     |
| Running Update Time | 602      |
----------------------------------
-2024-05-13 19:33:03.793997 ʱ-
| Itration            | 603      |
| Loss                | -312     |
| Real Det Return     | -591     |
| Real Sto Return     | -246     |
| Running Env Steps   | 3015000  |
| Running Forward KL  | 25.6     |
| Running Reverse KL  | 3.52     |
| Running Update Time | 603      |
----------------------------------
-2024-05-13 19:35:31.460891 ʱ-
| Itration            | 604      |
| Loss                | -333     |
| Real Det Return     | -345     |
| Real Sto Return     | -226     |
| Running Env Steps   | 3020000  |
| Running Forward KL  | 25.3     |
| Running Reverse KL  | 3.52     |
| Running Update Time | 604      |
----------------------------------
-2024-05-13 19:37:59.732933 ʱ-
| Itration            | 605      |
| Loss                | -285     |
| Real Det Return     | -627     |
| Real Sto Return     | -286     |
| Running Env Steps   | 3025000  |
| Running Forward KL  | 25.4     |
| Running Reverse KL  | 3.2      |
| Running Update Time | 605      |
----------------------------------
-2024-05-13 19:40:28.049050 ʱ-
| Itration            | 606      |
| Loss                | -288     |
| Real Det Return     | -219     |
| Real Sto Return     | -234     |
| Running Env Steps   | 3030000  |
| Running Forward KL  | 25.8     |
| Running Reverse KL  | 3.61     |
| Running Update Time | 606      |
----------------------------------
-2024-05-13 19:42:55.916005 ʱ-
| Itration            | 607      |
| Loss                | -327     |
| Real Det Return     | -225     |
| Real Sto Return     | -200     |
| Running Env Steps   | 3035000  |
| Running Forward KL  | 25.2     |
| Running Reverse KL  | 3.84     |
| Running Update Time | 607      |
----------------------------------
-2024-05-13 19:45:24.576454 ʱ-
| Itration            | 608      |
| Loss                | -312     |
| Real Det Return     | -449     |
| Real Sto Return     | -220     |
| Running Env Steps   | 3040000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 3.78     |
| Running Update Time | 608      |
----------------------------------
-2024-05-13 19:47:52.987711 ʱ-
| Itration            | 609      |
| Loss                | -296     |
| Real Det Return     | -242     |
| Real Sto Return     | -202     |
| Running Env Steps   | 3045000  |
| Running Forward KL  | 25.7     |
| Running Reverse KL  | 3.98     |
| Running Update Time | 609      |
----------------------------------
-2024-05-13 19:50:21.307455 ʱ-
| Itration            | 610      |
| Loss                | -288     |
| Real Det Return     | -350     |
| Real Sto Return     | -228     |
| Running Env Steps   | 3050000  |
| Running Forward KL  | 26.7     |
| Running Reverse KL  | 4.43     |
| Running Update Time | 610      |
----------------------------------
-2024-05-13 19:52:49.548973 ʱ-
| Itration            | 611      |
| Loss                | -267     |
| Real Det Return     | -567     |
| Real Sto Return     | -256     |
| Running Env Steps   | 3055000  |
| Running Forward KL  | 25       |
| Running Reverse KL  | 3.69     |
| Running Update Time | 611      |
----------------------------------
-2024-05-13 19:55:17.559243 ʱ-
| Itration            | 612      |
| Loss                | -292     |
| Real Det Return     | -507     |
| Real Sto Return     | -220     |
| Running Env Steps   | 3060000  |
| Running Forward KL  | 25.1     |
| Running Reverse KL  | 3.81     |
| Running Update Time | 612      |
----------------------------------
-2024-05-13 19:57:45.468508 ʱ-
| Itration            | 613      |
| Loss                | -310     |
| Real Det Return     | -580     |
| Real Sto Return     | -273     |
| Running Env Steps   | 3065000  |
| Running Forward KL  | 25.7     |
| Running Reverse KL  | 3.94     |
| Running Update Time | 613      |
----------------------------------
-2024-05-13 20:00:14.390373 ʱ-
| Itration            | 614      |
| Loss                | -352     |
| Real Det Return     | -165     |
| Real Sto Return     | -208     |
| Running Env Steps   | 3070000  |
| Running Forward KL  | 25.4     |
| Running Reverse KL  | 3.38     |
| Running Update Time | 614      |
----------------------------------
-2024-05-13 20:02:43.466151 ʱ-
| Itration            | 615      |
| Loss                | -307     |
| Real Det Return     | -87      |
| Real Sto Return     | -223     |
| Running Env Steps   | 3075000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 4.52     |
| Running Update Time | 615      |
----------------------------------
-2024-05-13 20:05:12.494042 ʱ-
| Itration            | 616      |
| Loss                | -263     |
| Real Det Return     | -108     |
| Real Sto Return     | -218     |
| Running Env Steps   | 3080000  |
| Running Forward KL  | 25.6     |
| Running Reverse KL  | 3.81     |
| Running Update Time | 616      |
----------------------------------
-2024-05-13 20:07:41.549471 ʱ-
| Itration            | 617      |
| Loss                | -314     |
| Real Det Return     | -75.9    |
| Real Sto Return     | -215     |
| Running Env Steps   | 3085000  |
| Running Forward KL  | 25.1     |
| Running Reverse KL  | 4.15     |
| Running Update Time | 617      |
----------------------------------
-2024-05-13 20:10:09.800196 ʱ-
| Itration            | 618      |
| Loss                | -347     |
| Real Det Return     | -325     |
| Real Sto Return     | -232     |
| Running Env Steps   | 3090000  |
| Running Forward KL  | 25.1     |
| Running Reverse KL  | 3.31     |
| Running Update Time | 618      |
----------------------------------
-2024-05-13 20:12:38.909499 ʱ-
| Itration            | 619      |
| Loss                | -285     |
| Real Det Return     | -159     |
| Real Sto Return     | -202     |
| Running Env Steps   | 3095000  |
| Running Forward KL  | 24.7     |
| Running Reverse KL  | 3.67     |
| Running Update Time | 619      |
----------------------------------
-2024-05-13 20:15:07.154421 ʱ-
| Itration            | 620      |
| Loss                | -340     |
| Real Det Return     | -310     |
| Real Sto Return     | -206     |
| Running Env Steps   | 3100000  |
| Running Forward KL  | 25.6     |
| Running Reverse KL  | 3.94     |
| Running Update Time | 620      |
----------------------------------
-2024-05-13 20:17:35.751824 ʱ-
| Itration            | 621      |
| Loss                | -325     |
| Real Det Return     | -687     |
| Real Sto Return     | -236     |
| Running Env Steps   | 3105000  |
| Running Forward KL  | 26.1     |
| Running Reverse KL  | 3.6      |
| Running Update Time | 621      |
----------------------------------
-2024-05-13 20:20:05.460010 ʱ-
| Itration            | 622      |
| Loss                | -306     |
| Real Det Return     | -302     |
| Real Sto Return     | -203     |
| Running Env Steps   | 3110000  |
| Running Forward KL  | 25       |
| Running Reverse KL  | 3.73     |
| Running Update Time | 622      |
----------------------------------
-2024-05-13 20:22:35.954527 ʱ-
| Itration            | 623      |
| Loss                | -330     |
| Real Det Return     | -163     |
| Real Sto Return     | -203     |
| Running Env Steps   | 3115000  |
| Running Forward KL  | 25.4     |
| Running Reverse KL  | 3.51     |
| Running Update Time | 623      |
----------------------------------
-2024-05-13 20:25:04.749224 ʱ-
| Itration            | 624      |
| Loss                | -341     |
| Real Det Return     | -285     |
| Real Sto Return     | -213     |
| Running Env Steps   | 3120000  |
| Running Forward KL  | 25.6     |
| Running Reverse KL  | 3.81     |
| Running Update Time | 624      |
----------------------------------
-2024-05-13 20:27:33.935556 ʱ-
| Itration            | 625      |
| Loss                | -357     |
| Real Det Return     | -170     |
| Real Sto Return     | -204     |
| Running Env Steps   | 3125000  |
| Running Forward KL  | 24.9     |
| Running Reverse KL  | 3.31     |
| Running Update Time | 625      |
----------------------------------
-2024-05-13 20:30:03.544732 ʱ-
| Itration            | 626      |
| Loss                | -324     |
| Real Det Return     | -427     |
| Real Sto Return     | -205     |
| Running Env Steps   | 3130000  |
| Running Forward KL  | 25.1     |
| Running Reverse KL  | 3.56     |
| Running Update Time | 626      |
----------------------------------
-2024-05-13 20:32:32.115792 ʱ-
| Itration            | 627      |
| Loss                | -300     |
| Real Det Return     | -370     |
| Real Sto Return     | -217     |
| Running Env Steps   | 3135000  |
| Running Forward KL  | 25.4     |
| Running Reverse KL  | 3.74     |
| Running Update Time | 627      |
----------------------------------
-2024-05-13 20:35:01.721906 ʱ-
| Itration            | 628      |
| Loss                | -321     |
| Real Det Return     | -589     |
| Real Sto Return     | -225     |
| Running Env Steps   | 3140000  |
| Running Forward KL  | 25.1     |
| Running Reverse KL  | 3.86     |
| Running Update Time | 628      |
----------------------------------
-2024-05-13 20:37:31.593698 ʱ-
| Itration            | 629      |
| Loss                | -289     |
| Real Det Return     | -712     |
| Real Sto Return     | -296     |
| Running Env Steps   | 3145000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 4.18     |
| Running Update Time | 629      |
----------------------------------
-2024-05-13 20:40:00.459581 ʱ-
| Itration            | 630      |
| Loss                | -316     |
| Real Det Return     | -155     |
| Real Sto Return     | -192     |
| Running Env Steps   | 3150000  |
| Running Forward KL  | 25.5     |
| Running Reverse KL  | 3.9      |
| Running Update Time | 630      |
----------------------------------
-2024-05-13 20:42:29.198899 ʱ-
| Itration            | 631      |
| Loss                | -256     |
| Real Det Return     | -140     |
| Real Sto Return     | -204     |
| Running Env Steps   | 3155000  |
| Running Forward KL  | 24.9     |
| Running Reverse KL  | 4.14     |
| Running Update Time | 631      |
----------------------------------
-2024-05-13 20:44:58.280432 ʱ-
| Itration            | 632      |
| Loss                | -307     |
| Real Det Return     | -384     |
| Real Sto Return     | -222     |
| Running Env Steps   | 3160000  |
| Running Forward KL  | 25.1     |
| Running Reverse KL  | 3.47     |
| Running Update Time | 632      |
----------------------------------
-2024-05-13 20:47:27.129372 ʱ-
| Itration            | 633      |
| Loss                | -277     |
| Real Det Return     | -175     |
| Real Sto Return     | -256     |
| Running Env Steps   | 3165000  |
| Running Forward KL  | 25.3     |
| Running Reverse KL  | 4.33     |
| Running Update Time | 633      |
----------------------------------
-2024-05-13 20:49:55.570636 ʱ-
| Itration            | 634      |
| Loss                | -342     |
| Real Det Return     | -103     |
| Real Sto Return     | -259     |
| Running Env Steps   | 3170000  |
| Running Forward KL  | 26.2     |
| Running Reverse KL  | 4.12     |
| Running Update Time | 634      |
----------------------------------
-2024-05-13 20:52:24.562425 ʱ-
| Itration            | 635      |
| Loss                | -274     |
| Real Det Return     | -187     |
| Real Sto Return     | -284     |
| Running Env Steps   | 3175000  |
| Running Forward KL  | 24.5     |
| Running Reverse KL  | 4.53     |
| Running Update Time | 635      |
----------------------------------
-2024-05-13 20:54:53.633942 ʱ-
| Itration            | 636      |
| Loss                | -313     |
| Real Det Return     | -507     |
| Real Sto Return     | -230     |
| Running Env Steps   | 3180000  |
| Running Forward KL  | 25.7     |
| Running Reverse KL  | 3.98     |
| Running Update Time | 636      |
----------------------------------
-2024-05-13 20:57:23.129646 ʱ-
| Itration            | 637      |
| Loss                | -336     |
| Real Det Return     | -114     |
| Real Sto Return     | -205     |
| Running Env Steps   | 3185000  |
| Running Forward KL  | 25.2     |
| Running Reverse KL  | 4.39     |
| Running Update Time | 637      |
----------------------------------
-2024-05-13 20:59:52.860367 ʱ-
| Itration            | 638      |
| Loss                | -322     |
| Real Det Return     | -472     |
| Real Sto Return     | -208     |
| Running Env Steps   | 3190000  |
| Running Forward KL  | 25.5     |
| Running Reverse KL  | 4        |
| Running Update Time | 638      |
----------------------------------
-2024-05-13 21:02:21.348053 ʱ-
| Itration            | 639      |
| Loss                | -324     |
| Real Det Return     | -256     |
| Real Sto Return     | -184     |
| Running Env Steps   | 3195000  |
| Running Forward KL  | 25.1     |
| Running Reverse KL  | 3.78     |
| Running Update Time | 639      |
----------------------------------
-2024-05-13 21:04:50.490582 ʱ-
| Itration            | 640      |
| Loss                | -324     |
| Real Det Return     | -138     |
| Real Sto Return     | -189     |
| Running Env Steps   | 3200000  |
| Running Forward KL  | 24.5     |
| Running Reverse KL  | 3.51     |
| Running Update Time | 640      |
----------------------------------
-2024-05-13 21:07:20.439869 ʱ-
| Itration            | 641      |
| Loss                | -327     |
| Real Det Return     | -157     |
| Real Sto Return     | -217     |
| Running Env Steps   | 3205000  |
| Running Forward KL  | 25.1     |
| Running Reverse KL  | 3.9      |
| Running Update Time | 641      |
----------------------------------
-2024-05-13 21:09:49.288578 ʱ-
| Itration            | 642      |
| Loss                | -276     |
| Real Det Return     | -533     |
| Real Sto Return     | -231     |
| Running Env Steps   | 3210000  |
| Running Forward KL  | 25       |
| Running Reverse KL  | 3.59     |
| Running Update Time | 642      |
----------------------------------
-2024-05-13 21:12:17.842338 ʱ-
| Itration            | 643      |
| Loss                | -328     |
| Real Det Return     | -264     |
| Real Sto Return     | -253     |
| Running Env Steps   | 3215000  |
| Running Forward KL  | 26.1     |
| Running Reverse KL  | 4.78     |
| Running Update Time | 643      |
----------------------------------
-2024-05-13 21:14:46.873336 ʱ-
| Itration            | 644      |
| Loss                | -335     |
| Real Det Return     | -538     |
| Real Sto Return     | -205     |
| Running Env Steps   | 3220000  |
| Running Forward KL  | 25.5     |
| Running Reverse KL  | 4.31     |
| Running Update Time | 644      |
----------------------------------
-2024-05-13 21:17:17.073666 ʱ-
| Itration            | 645      |
| Loss                | -330     |
| Real Det Return     | -124     |
| Real Sto Return     | -209     |
| Running Env Steps   | 3225000  |
| Running Forward KL  | 25.3     |
| Running Reverse KL  | 3.82     |
| Running Update Time | 645      |
----------------------------------
-2024-05-13 21:19:46.518110 ʱ-
| Itration            | 646      |
| Loss                | -350     |
| Real Det Return     | -173     |
| Real Sto Return     | -234     |
| Running Env Steps   | 3230000  |
| Running Forward KL  | 26.1     |
| Running Reverse KL  | 3.97     |
| Running Update Time | 646      |
----------------------------------
-2024-05-13 21:22:15.173464 ʱ-
| Itration            | 647      |
| Loss                | -335     |
| Real Det Return     | -121     |
| Real Sto Return     | -231     |
| Running Env Steps   | 3235000  |
| Running Forward KL  | 25       |
| Running Reverse KL  | 3.72     |
| Running Update Time | 647      |
----------------------------------
-2024-05-13 21:24:44.275902 ʱ-
| Itration            | 648      |
| Loss                | -342     |
| Real Det Return     | -215     |
| Real Sto Return     | -199     |
| Running Env Steps   | 3240000  |
| Running Forward KL  | 25.1     |
| Running Reverse KL  | 3.62     |
| Running Update Time | 648      |
----------------------------------
-2024-05-13 21:27:15.042214 ʱ-
| Itration            | 649      |
| Loss                | -346     |
| Real Det Return     | -214     |
| Real Sto Return     | -217     |
| Running Env Steps   | 3245000  |
| Running Forward KL  | 25.5     |
| Running Reverse KL  | 4.06     |
| Running Update Time | 649      |
----------------------------------
-2024-05-13 21:29:46.242378 ʱ-
| Itration            | 650      |
| Loss                | -354     |
| Real Det Return     | -591     |
| Real Sto Return     | -220     |
| Running Env Steps   | 3250000  |
| Running Forward KL  | 25.1     |
| Running Reverse KL  | 3.32     |
| Running Update Time | 650      |
----------------------------------
-2024-05-13 21:32:14.919819 ʱ-
| Itration            | 651      |
| Loss                | -373     |
| Real Det Return     | -617     |
| Real Sto Return     | -274     |
| Running Env Steps   | 3255000  |
| Running Forward KL  | 25.5     |
| Running Reverse KL  | 3.79     |
| Running Update Time | 651      |
----------------------------------
-2024-05-13 21:34:44.399240 ʱ-
| Itration            | 652      |
| Loss                | -306     |
| Real Det Return     | -236     |
| Real Sto Return     | -203     |
| Running Env Steps   | 3260000  |
| Running Forward KL  | 25       |
| Running Reverse KL  | 3.99     |
| Running Update Time | 652      |
----------------------------------
-2024-05-13 21:37:13.591651 ʱ-
| Itration            | 653      |
| Loss                | -302     |
| Real Det Return     | -278     |
| Real Sto Return     | -241     |
| Running Env Steps   | 3265000  |
| Running Forward KL  | 24.9     |
| Running Reverse KL  | 3.64     |
| Running Update Time | 653      |
----------------------------------
-2024-05-13 21:39:42.512855 ʱ-
| Itration            | 654      |
| Loss                | -295     |
| Real Det Return     | -337     |
| Real Sto Return     | -203     |
| Running Env Steps   | 3270000  |
| Running Forward KL  | 25       |
| Running Reverse KL  | 3.66     |
| Running Update Time | 654      |
----------------------------------
-2024-05-13 21:42:11.654183 ʱ-
| Itration            | 655      |
| Loss                | -329     |
| Real Det Return     | -354     |
| Real Sto Return     | -193     |
| Running Env Steps   | 3275000  |
| Running Forward KL  | 24.7     |
| Running Reverse KL  | 3.52     |
| Running Update Time | 655      |
----------------------------------
-2024-05-13 21:44:41.055278 ʱ-
| Itration            | 656      |
| Loss                | -338     |
| Real Det Return     | -183     |
| Real Sto Return     | -222     |
| Running Env Steps   | 3280000  |
| Running Forward KL  | 25.6     |
| Running Reverse KL  | 4.01     |
| Running Update Time | 656      |
----------------------------------
-2024-05-13 21:47:11.101528 ʱ-
| Itration            | 657      |
| Loss                | -328     |
| Real Det Return     | -416     |
| Real Sto Return     | -206     |
| Running Env Steps   | 3285000  |
| Running Forward KL  | 25.9     |
| Running Reverse KL  | 4.21     |
| Running Update Time | 657      |
----------------------------------
-2024-05-13 21:49:40.975366 ʱ-
| Itration            | 658      |
| Loss                | -311     |
| Real Det Return     | -272     |
| Real Sto Return     | -216     |
| Running Env Steps   | 3290000  |
| Running Forward KL  | 25.5     |
| Running Reverse KL  | 4.02     |
| Running Update Time | 658      |
----------------------------------
-2024-05-13 21:52:11.463547 ʱ-
| Itration            | 659      |
| Loss                | -331     |
| Real Det Return     | -323     |
| Real Sto Return     | -195     |
| Running Env Steps   | 3295000  |
| Running Forward KL  | 24.7     |
| Running Reverse KL  | 3.63     |
| Running Update Time | 659      |
----------------------------------
-2024-05-13 21:54:41.493248 ʱ-
| Itration            | 660      |
| Loss                | -315     |
| Real Det Return     | -233     |
| Real Sto Return     | -205     |
| Running Env Steps   | 3300000  |
| Running Forward KL  | 24.5     |
| Running Reverse KL  | 3.91     |
| Running Update Time | 660      |
----------------------------------
-2024-05-13 21:57:10.817115 ʱ-
| Itration            | 661      |
| Loss                | -298     |
| Real Det Return     | -323     |
| Real Sto Return     | -202     |
| Running Env Steps   | 3305000  |
| Running Forward KL  | 25       |
| Running Reverse KL  | 3.7      |
| Running Update Time | 661      |
----------------------------------
-2024-05-13 21:59:40.780994 ʱ-
| Itration            | 662      |
| Loss                | -335     |
| Real Det Return     | -463     |
| Real Sto Return     | -247     |
| Running Env Steps   | 3310000  |
| Running Forward KL  | 24.9     |
| Running Reverse KL  | 4.05     |
| Running Update Time | 662      |
----------------------------------
-2024-05-13 22:02:10.225675 ʱ-
| Itration            | 663      |
| Loss                | -307     |
| Real Det Return     | -447     |
| Real Sto Return     | -257     |
| Running Env Steps   | 3315000  |
| Running Forward KL  | 24.9     |
| Running Reverse KL  | 4.13     |
| Running Update Time | 663      |
----------------------------------
-2024-05-13 22:04:40.169405 ʱ-
| Itration            | 664      |
| Loss                | -341     |
| Real Det Return     | -327     |
| Real Sto Return     | -187     |
| Running Env Steps   | 3320000  |
| Running Forward KL  | 25       |
| Running Reverse KL  | 3.64     |
| Running Update Time | 664      |
----------------------------------
-2024-05-13 22:07:09.084096 ʱ-
| Itration            | 665      |
| Loss                | -349     |
| Real Det Return     | -205     |
| Real Sto Return     | -210     |
| Running Env Steps   | 3325000  |
| Running Forward KL  | 24.1     |
| Running Reverse KL  | 3.69     |
| Running Update Time | 665      |
----------------------------------
-2024-05-13 22:09:38.385759 ʱ-
| Itration            | 666      |
| Loss                | -336     |
| Real Det Return     | -144     |
| Real Sto Return     | -207     |
| Running Env Steps   | 3330000  |
| Running Forward KL  | 24       |
| Running Reverse KL  | 3.52     |
| Running Update Time | 666      |
----------------------------------
-2024-05-13 22:12:08.338807 ʱ-
| Itration            | 667      |
| Loss                | -344     |
| Real Det Return     | -305     |
| Real Sto Return     | -207     |
| Running Env Steps   | 3335000  |
| Running Forward KL  | 24.6     |
| Running Reverse KL  | 3.35     |
| Running Update Time | 667      |
----------------------------------
-2024-05-13 22:14:38.074984 ʱ-
| Itration            | 668      |
| Loss                | -305     |
| Real Det Return     | -373     |
| Real Sto Return     | -194     |
| Running Env Steps   | 3340000  |
| Running Forward KL  | 23.6     |
| Running Reverse KL  | 3.49     |
| Running Update Time | 668      |
----------------------------------
-2024-05-13 22:17:07.279408 ʱ-
| Itration            | 669      |
| Loss                | -322     |
| Real Det Return     | -374     |
| Real Sto Return     | -199     |
| Running Env Steps   | 3345000  |
| Running Forward KL  | 24.7     |
| Running Reverse KL  | 4.05     |
| Running Update Time | 669      |
----------------------------------
-2024-05-13 22:19:36.534650 ʱ-
| Itration            | 670      |
| Loss                | -338     |
| Real Det Return     | -165     |
| Real Sto Return     | -191     |
| Running Env Steps   | 3350000  |
| Running Forward KL  | 24.8     |
| Running Reverse KL  | 3.97     |
| Running Update Time | 670      |
----------------------------------
-2024-05-13 22:22:05.372087 ʱ-
| Itration            | 671      |
| Loss                | -320     |
| Real Det Return     | -323     |
| Real Sto Return     | -188     |
| Running Env Steps   | 3355000  |
| Running Forward KL  | 24.3     |
| Running Reverse KL  | 3.68     |
| Running Update Time | 671      |
----------------------------------
-2024-05-13 22:24:35.186596 ʱ-
| Itration            | 672      |
| Loss                | -321     |
| Real Det Return     | -188     |
| Real Sto Return     | -221     |
| Running Env Steps   | 3360000  |
| Running Forward KL  | 24.8     |
| Running Reverse KL  | 4.11     |
| Running Update Time | 672      |
----------------------------------
-2024-05-13 22:27:03.866002 ʱ-
| Itration            | 673      |
| Loss                | -300     |
| Real Det Return     | -190     |
| Real Sto Return     | -184     |
| Running Env Steps   | 3365000  |
| Running Forward KL  | 24.2     |
| Running Reverse KL  | 3.58     |
| Running Update Time | 673      |
----------------------------------
-2024-05-13 22:29:33.169746 ʱ-
| Itration            | 674      |
| Loss                | -337     |
| Real Det Return     | -202     |
| Real Sto Return     | -201     |
| Running Env Steps   | 3370000  |
| Running Forward KL  | 25.1     |
| Running Reverse KL  | 3.97     |
| Running Update Time | 674      |
----------------------------------
-2024-05-13 22:32:02.529754 ʱ-
| Itration            | 675      |
| Loss                | -287     |
| Real Det Return     | -355     |
| Real Sto Return     | -367     |
| Running Env Steps   | 3375000  |
| Running Forward KL  | 25.5     |
| Running Reverse KL  | 4.89     |
| Running Update Time | 675      |
----------------------------------
-2024-05-13 22:34:32.005398 ʱ-
| Itration            | 676      |
| Loss                | -312     |
| Real Det Return     | -162     |
| Real Sto Return     | -220     |
| Running Env Steps   | 3380000  |
| Running Forward KL  | 24.3     |
| Running Reverse KL  | 4.22     |
| Running Update Time | 676      |
----------------------------------
-2024-05-13 22:37:01.376788 ʱ-
| Itration            | 677      |
| Loss                | -312     |
| Real Det Return     | -218     |
| Real Sto Return     | -205     |
| Running Env Steps   | 3385000  |
| Running Forward KL  | 24.4     |
| Running Reverse KL  | 4.08     |
| Running Update Time | 677      |
----------------------------------
-2024-05-13 22:39:30.166918 ʱ-
| Itration            | 678      |
| Loss                | -305     |
| Real Det Return     | -197     |
| Real Sto Return     | -300     |
| Running Env Steps   | 3390000  |
| Running Forward KL  | 25.4     |
| Running Reverse KL  | 5.03     |
| Running Update Time | 678      |
----------------------------------
-2024-05-13 22:41:59.968954 ʱ-
| Itration            | 679      |
| Loss                | -336     |
| Real Det Return     | -148     |
| Real Sto Return     | -208     |
| Running Env Steps   | 3395000  |
| Running Forward KL  | 24.6     |
| Running Reverse KL  | 4.04     |
| Running Update Time | 679      |
----------------------------------
-2024-05-13 22:44:29.224314 ʱ-
| Itration            | 680      |
| Loss                | -363     |
| Real Det Return     | -146     |
| Real Sto Return     | -202     |
| Running Env Steps   | 3400000  |
| Running Forward KL  | 24.8     |
| Running Reverse KL  | 3.97     |
| Running Update Time | 680      |
----------------------------------
-2024-05-13 22:46:58.873395 ʱ-
| Itration            | 681      |
| Loss                | -314     |
| Real Det Return     | -170     |
| Real Sto Return     | -218     |
| Running Env Steps   | 3405000  |
| Running Forward KL  | 24.7     |
| Running Reverse KL  | 3.71     |
| Running Update Time | 681      |
----------------------------------
-2024-05-13 22:49:28.536054 ʱ-
| Itration            | 682      |
| Loss                | -348     |
| Real Det Return     | -101     |
| Real Sto Return     | -222     |
| Running Env Steps   | 3410000  |
| Running Forward KL  | 25       |
| Running Reverse KL  | 4.16     |
| Running Update Time | 682      |
----------------------------------
-2024-05-13 22:51:57.603291 ʱ-
| Itration            | 683      |
| Loss                | -316     |
| Real Det Return     | -104     |
| Real Sto Return     | -227     |
| Running Env Steps   | 3415000  |
| Running Forward KL  | 25.1     |
| Running Reverse KL  | 4.55     |
| Running Update Time | 683      |
----------------------------------
-2024-05-13 22:54:26.747770 ʱ-
| Itration            | 684      |
| Loss                | -334     |
| Real Det Return     | -130     |
| Real Sto Return     | -192     |
| Running Env Steps   | 3420000  |
| Running Forward KL  | 25.6     |
| Running Reverse KL  | 4.64     |
| Running Update Time | 684      |
----------------------------------
-2024-05-13 22:56:56.458116 ʱ-
| Itration            | 685      |
| Loss                | -328     |
| Real Det Return     | -315     |
| Real Sto Return     | -189     |
| Running Env Steps   | 3425000  |
| Running Forward KL  | 24.4     |
| Running Reverse KL  | 3.59     |
| Running Update Time | 685      |
----------------------------------
-2024-05-13 22:59:26.921535 ʱ-
| Itration            | 686      |
| Loss                | -341     |
| Real Det Return     | -468     |
| Real Sto Return     | -254     |
| Running Env Steps   | 3430000  |
| Running Forward KL  | 24.5     |
| Running Reverse KL  | 3.83     |
| Running Update Time | 686      |
----------------------------------
-2024-05-13 23:01:56.161983 ʱ-
| Itration            | 687      |
| Loss                | -321     |
| Real Det Return     | -145     |
| Real Sto Return     | -196     |
| Running Env Steps   | 3435000  |
| Running Forward KL  | 24.5     |
| Running Reverse KL  | 4.05     |
| Running Update Time | 687      |
----------------------------------
-2024-05-13 23:04:25.111131 ʱ-
| Itration            | 688      |
| Loss                | -328     |
| Real Det Return     | -429     |
| Real Sto Return     | -268     |
| Running Env Steps   | 3440000  |
| Running Forward KL  | 25.1     |
| Running Reverse KL  | 3.76     |
| Running Update Time | 688      |
----------------------------------
-2024-05-13 23:06:55.438693 ʱ-
| Itration            | 689      |
| Loss                | -350     |
| Real Det Return     | -460     |
| Real Sto Return     | -206     |
| Running Env Steps   | 3445000  |
| Running Forward KL  | 24.6     |
| Running Reverse KL  | 3.99     |
| Running Update Time | 689      |
----------------------------------
-2024-05-13 23:09:25.806009 ʱ-
| Itration            | 690      |
| Loss                | -331     |
| Real Det Return     | -562     |
| Real Sto Return     | -318     |
| Running Env Steps   | 3450000  |
| Running Forward KL  | 24.6     |
| Running Reverse KL  | 3.51     |
| Running Update Time | 690      |
----------------------------------
-2024-05-13 23:11:55.030583 ʱ-
| Itration            | 691      |
| Loss                | -367     |
| Real Det Return     | -520     |
| Real Sto Return     | -243     |
| Running Env Steps   | 3455000  |
| Running Forward KL  | 25       |
| Running Reverse KL  | 4.17     |
| Running Update Time | 691      |
----------------------------------
-2024-05-13 23:14:24.462165 ʱ-
| Itration            | 692      |
| Loss                | -324     |
| Real Det Return     | -313     |
| Real Sto Return     | -235     |
| Running Env Steps   | 3460000  |
| Running Forward KL  | 24.9     |
| Running Reverse KL  | 4.09     |
| Running Update Time | 692      |
----------------------------------
-2024-05-13 23:16:53.551456 ʱ-
| Itration            | 693      |
| Loss                | -361     |
| Real Det Return     | -252     |
| Real Sto Return     | -183     |
| Running Env Steps   | 3465000  |
| Running Forward KL  | 24.6     |
| Running Reverse KL  | 3.69     |
| Running Update Time | 693      |
----------------------------------
-2024-05-13 23:19:22.911052 ʱ-
| Itration            | 694      |
| Loss                | -377     |
| Real Det Return     | -109     |
| Real Sto Return     | -202     |
| Running Env Steps   | 3470000  |
| Running Forward KL  | 24.4     |
| Running Reverse KL  | 3.97     |
| Running Update Time | 694      |
----------------------------------
-2024-05-13 23:21:52.287068 ʱ-
| Itration            | 695      |
| Loss                | -349     |
| Real Det Return     | -554     |
| Real Sto Return     | -256     |
| Running Env Steps   | 3475000  |
| Running Forward KL  | 24.3     |
| Running Reverse KL  | 3.83     |
| Running Update Time | 695      |
----------------------------------
-2024-05-13 23:24:21.406969 ʱ-
| Itration            | 696      |
| Loss                | -325     |
| Real Det Return     | -379     |
| Real Sto Return     | -217     |
| Running Env Steps   | 3480000  |
| Running Forward KL  | 24.2     |
| Running Reverse KL  | 3.53     |
| Running Update Time | 696      |
----------------------------------
-2024-05-13 23:26:50.579378 ʱ-
| Itration            | 697      |
| Loss                | -307     |
| Real Det Return     | -103     |
| Real Sto Return     | -202     |
| Running Env Steps   | 3485000  |
| Running Forward KL  | 23.8     |
| Running Reverse KL  | 4.25     |
| Running Update Time | 697      |
----------------------------------
-2024-05-13 23:29:27.232279 ʱ-
| Itration            | 698      |
| Loss                | -327     |
| Real Det Return     | -267     |
| Real Sto Return     | -185     |
| Running Env Steps   | 3490000  |
| Running Forward KL  | 24.6     |
| Running Reverse KL  | 4.02     |
| Running Update Time | 698      |
----------------------------------
-2024-05-13 23:32:13.300545 ʱ-
| Itration            | 699      |
| Loss                | -333     |
| Real Det Return     | -245     |
| Real Sto Return     | -191     |
| Running Env Steps   | 3495000  |
| Running Forward KL  | 25.2     |
| Running Reverse KL  | 4.39     |
| Running Update Time | 699      |
----------------------------------
-2024-05-13 23:34:42.890381 ʱ-
| Itration            | 700      |
| Loss                | -346     |
| Real Det Return     | -271     |
| Real Sto Return     | -226     |
| Running Env Steps   | 3500000  |
| Running Forward KL  | 24.1     |
| Running Reverse KL  | 3.69     |
| Running Update Time | 700      |
----------------------------------
-2024-05-13 23:37:12.556238 ʱ-
| Itration            | 701      |
| Loss                | -336     |
| Real Det Return     | -321     |
| Real Sto Return     | -191     |
| Running Env Steps   | 3505000  |
| Running Forward KL  | 24.9     |
| Running Reverse KL  | 4.27     |
| Running Update Time | 701      |
----------------------------------
-2024-05-13 23:39:43.964839 ʱ-
| Itration            | 702      |
| Loss                | -367     |
| Real Det Return     | -334     |
| Real Sto Return     | -207     |
| Running Env Steps   | 3510000  |
| Running Forward KL  | 23.6     |
| Running Reverse KL  | 3.37     |
| Running Update Time | 702      |
----------------------------------
-2024-05-13 23:42:11.006655 ʱ-
| Itration            | 703      |
| Loss                | -328     |
| Real Det Return     | -271     |
| Real Sto Return     | -266     |
| Running Env Steps   | 3515000  |
| Running Forward KL  | 25.2     |
| Running Reverse KL  | 4.51     |
| Running Update Time | 703      |
----------------------------------
-2024-05-13 23:44:39.966942 ʱ-
| Itration            | 704      |
| Loss                | -349     |
| Real Det Return     | -171     |
| Real Sto Return     | -217     |
| Running Env Steps   | 3520000  |
| Running Forward KL  | 24       |
| Running Reverse KL  | 4.04     |
| Running Update Time | 704      |
----------------------------------
-2024-05-13 23:47:09.080771 ʱ-
| Itration            | 705      |
| Loss                | -303     |
| Real Det Return     | -514     |
| Real Sto Return     | -256     |
| Running Env Steps   | 3525000  |
| Running Forward KL  | 24.5     |
| Running Reverse KL  | 4.35     |
| Running Update Time | 705      |
----------------------------------
-2024-05-13 23:49:39.854712 ʱ-
| Itration            | 706      |
| Loss                | -297     |
| Real Det Return     | -266     |
| Real Sto Return     | -186     |
| Running Env Steps   | 3530000  |
| Running Forward KL  | 24.1     |
| Running Reverse KL  | 3.98     |
| Running Update Time | 706      |
----------------------------------
-2024-05-13 23:52:09.784871 ʱ-
| Itration            | 707      |
| Loss                | -288     |
| Real Det Return     | -196     |
| Real Sto Return     | -184     |
| Running Env Steps   | 3535000  |
| Running Forward KL  | 23       |
| Running Reverse KL  | 3.78     |
| Running Update Time | 707      |
----------------------------------
-2024-05-13 23:54:39.308030 ʱ-
| Itration            | 708      |
| Loss                | -297     |
| Real Det Return     | -208     |
| Real Sto Return     | -180     |
| Running Env Steps   | 3540000  |
| Running Forward KL  | 23.6     |
| Running Reverse KL  | 3.61     |
| Running Update Time | 708      |
----------------------------------
-2024-05-13 23:57:09.155885 ʱ-
| Itration            | 709      |
| Loss                | -359     |
| Real Det Return     | -544     |
| Real Sto Return     | -257     |
| Running Env Steps   | 3545000  |
| Running Forward KL  | 24.9     |
| Running Reverse KL  | 4.23     |
| Running Update Time | 709      |
----------------------------------
-2024-05-13 23:59:39.242840 ʱ-
| Itration            | 710      |
| Loss                | -316     |
| Real Det Return     | -350     |
| Real Sto Return     | -196     |
| Running Env Steps   | 3550000  |
| Running Forward KL  | 23.9     |
| Running Reverse KL  | 3.52     |
| Running Update Time | 710      |
----------------------------------
-2024-05-14 00:02:08.787655 ʱ-
| Itration            | 711      |
| Loss                | -317     |
| Real Det Return     | -573     |
| Real Sto Return     | -298     |
| Running Env Steps   | 3555000  |
| Running Forward KL  | 23.9     |
| Running Reverse KL  | 3.78     |
| Running Update Time | 711      |
----------------------------------
-2024-05-14 00:04:38.201941 ʱ-
| Itration            | 712      |
| Loss                | -339     |
| Real Det Return     | -201     |
| Real Sto Return     | -207     |
| Running Env Steps   | 3560000  |
| Running Forward KL  | 24.7     |
| Running Reverse KL  | 4.16     |
| Running Update Time | 712      |
----------------------------------
-2024-05-14 00:07:08.071845 ʱ-
| Itration            | 713      |
| Loss                | -374     |
| Real Det Return     | -444     |
| Real Sto Return     | -277     |
| Running Env Steps   | 3565000  |
| Running Forward KL  | 24.3     |
| Running Reverse KL  | 3.37     |
| Running Update Time | 713      |
----------------------------------
-2024-05-14 00:09:37.130204 ʱ-
| Itration            | 714      |
| Loss                | -320     |
| Real Det Return     | -583     |
| Real Sto Return     | -285     |
| Running Env Steps   | 3570000  |
| Running Forward KL  | 24.7     |
| Running Reverse KL  | 3.85     |
| Running Update Time | 714      |
----------------------------------
-2024-05-14 00:12:06.527884 ʱ-
| Itration            | 715      |
| Loss                | -353     |
| Real Det Return     | -312     |
| Real Sto Return     | -231     |
| Running Env Steps   | 3575000  |
| Running Forward KL  | 24.4     |
| Running Reverse KL  | 3.84     |
| Running Update Time | 715      |
----------------------------------
-2024-05-14 00:14:35.485718 ʱ-
| Itration            | 716      |
| Loss                | -334     |
| Real Det Return     | -330     |
| Real Sto Return     | -185     |
| Running Env Steps   | 3580000  |
| Running Forward KL  | 24.5     |
| Running Reverse KL  | 3.95     |
| Running Update Time | 716      |
----------------------------------
-2024-05-14 00:17:05.120177 ʱ-
| Itration            | 717      |
| Loss                | -314     |
| Real Det Return     | -508     |
| Real Sto Return     | -263     |
| Running Env Steps   | 3585000  |
| Running Forward KL  | 24.4     |
| Running Reverse KL  | 4.37     |
| Running Update Time | 717      |
----------------------------------
-2024-05-14 00:19:34.659845 ʱ-
| Itration            | 718      |
| Loss                | -360     |
| Real Det Return     | -377     |
| Real Sto Return     | -209     |
| Running Env Steps   | 3590000  |
| Running Forward KL  | 24.2     |
| Running Reverse KL  | 4.07     |
| Running Update Time | 718      |
----------------------------------
-2024-05-14 00:22:03.384663 ʱ-
| Itration            | 719      |
| Loss                | -382     |
| Real Det Return     | -258     |
| Real Sto Return     | -188     |
| Running Env Steps   | 3595000  |
| Running Forward KL  | 24       |
| Running Reverse KL  | 4.03     |
| Running Update Time | 719      |
----------------------------------
-2024-05-14 00:24:32.529616 ʱ-
| Itration            | 720      |
| Loss                | -391     |
| Real Det Return     | -555     |
| Real Sto Return     | -318     |
| Running Env Steps   | 3600000  |
| Running Forward KL  | 24.7     |
| Running Reverse KL  | 4.25     |
| Running Update Time | 720      |
----------------------------------
-2024-05-14 00:27:03.221515 ʱ-
| Itration            | 721      |
| Loss                | -374     |
| Real Det Return     | -248     |
| Real Sto Return     | -190     |
| Running Env Steps   | 3605000  |
| Running Forward KL  | 24.5     |
| Running Reverse KL  | 3.81     |
| Running Update Time | 721      |
----------------------------------
-2024-05-14 00:29:36.477386 ʱ-
| Itration            | 722      |
| Loss                | -319     |
| Real Det Return     | -140     |
| Real Sto Return     | -211     |
| Running Env Steps   | 3610000  |
| Running Forward KL  | 24.2     |
| Running Reverse KL  | 4.24     |
| Running Update Time | 722      |
----------------------------------
-2024-05-14 00:32:10.954003 ʱ-
| Itration            | 723      |
| Loss                | -363     |
| Real Det Return     | -263     |
| Real Sto Return     | -190     |
| Running Env Steps   | 3615000  |
| Running Forward KL  | 23.5     |
| Running Reverse KL  | 3.62     |
| Running Update Time | 723      |
----------------------------------
-2024-05-14 00:34:40.864775 ʱ-
| Itration            | 724      |
| Loss                | -348     |
| Real Det Return     | -113     |
| Real Sto Return     | -253     |
| Running Env Steps   | 3620000  |
| Running Forward KL  | 24       |
| Running Reverse KL  | 3.9      |
| Running Update Time | 724      |
----------------------------------
-2024-05-14 00:37:10.166866 ʱ-
| Itration            | 725      |
| Loss                | -368     |
| Real Det Return     | -299     |
| Real Sto Return     | -313     |
| Running Env Steps   | 3625000  |
| Running Forward KL  | 25.3     |
| Running Reverse KL  | 4.65     |
| Running Update Time | 725      |
----------------------------------
-2024-05-14 00:39:39.623821 ʱ-
| Itration            | 726      |
| Loss                | -383     |
| Real Det Return     | -220     |
| Real Sto Return     | -241     |
| Running Env Steps   | 3630000  |
| Running Forward KL  | 23.8     |
| Running Reverse KL  | 4.07     |
| Running Update Time | 726      |
----------------------------------
-2024-05-14 00:42:09.472212 ʱ-
| Itration            | 727      |
| Loss                | -352     |
| Real Det Return     | -355     |
| Real Sto Return     | -197     |
| Running Env Steps   | 3635000  |
| Running Forward KL  | 24.1     |
| Running Reverse KL  | 3.92     |
| Running Update Time | 727      |
----------------------------------
-2024-05-14 00:44:38.538618 ʱ-
| Itration            | 728      |
| Loss                | -375     |
| Real Det Return     | -162     |
| Real Sto Return     | -186     |
| Running Env Steps   | 3640000  |
| Running Forward KL  | 24.1     |
| Running Reverse KL  | 3.97     |
| Running Update Time | 728      |
----------------------------------
-2024-05-14 00:47:08.449727 ʱ-
| Itration            | 729      |
| Loss                | -332     |
| Real Det Return     | -260     |
| Real Sto Return     | -204     |
| Running Env Steps   | 3645000  |
| Running Forward KL  | 23.9     |
| Running Reverse KL  | 3.82     |
| Running Update Time | 729      |
----------------------------------
-2024-05-14 00:49:38.092370 ʱ-
| Itration            | 730      |
| Loss                | -332     |
| Real Det Return     | -328     |
| Real Sto Return     | -184     |
| Running Env Steps   | 3650000  |
| Running Forward KL  | 24       |
| Running Reverse KL  | 3.93     |
| Running Update Time | 730      |
----------------------------------
-2024-05-14 00:52:08.231927 ʱ-
| Itration            | 731      |
| Loss                | -349     |
| Real Det Return     | -294     |
| Real Sto Return     | -187     |
| Running Env Steps   | 3655000  |
| Running Forward KL  | 23.9     |
| Running Reverse KL  | 3.7      |
| Running Update Time | 731      |
----------------------------------
-2024-05-14 00:54:38.354738 ʱ-
| Itration            | 732      |
| Loss                | -353     |
| Real Det Return     | -211     |
| Real Sto Return     | -177     |
| Running Env Steps   | 3660000  |
| Running Forward KL  | 24       |
| Running Reverse KL  | 4.18     |
| Running Update Time | 732      |
----------------------------------
-2024-05-14 00:57:07.986135 ʱ-
| Itration            | 733      |
| Loss                | -357     |
| Real Det Return     | -215     |
| Real Sto Return     | -188     |
| Running Env Steps   | 3665000  |
| Running Forward KL  | 23.9     |
| Running Reverse KL  | 4.32     |
| Running Update Time | 733      |
----------------------------------
-2024-05-14 00:59:36.960003 ʱ-
| Itration            | 734      |
| Loss                | -343     |
| Real Det Return     | -168     |
| Real Sto Return     | -181     |
| Running Env Steps   | 3670000  |
| Running Forward KL  | 23.5     |
| Running Reverse KL  | 4.01     |
| Running Update Time | 734      |
----------------------------------
-2024-05-14 01:02:07.157886 ʱ-
| Itration            | 735      |
| Loss                | -351     |
| Real Det Return     | -308     |
| Real Sto Return     | -203     |
| Running Env Steps   | 3675000  |
| Running Forward KL  | 23.8     |
| Running Reverse KL  | 3.95     |
| Running Update Time | 735      |
----------------------------------
-2024-05-14 01:04:36.325607 ʱ-
| Itration            | 736      |
| Loss                | -373     |
| Real Det Return     | -498     |
| Real Sto Return     | -227     |
| Running Env Steps   | 3680000  |
| Running Forward KL  | 23.7     |
| Running Reverse KL  | 3.86     |
| Running Update Time | 736      |
----------------------------------
-2024-05-14 01:07:05.958220 ʱ-
| Itration            | 737      |
| Loss                | -371     |
| Real Det Return     | -347     |
| Real Sto Return     | -197     |
| Running Env Steps   | 3685000  |
| Running Forward KL  | 24.2     |
| Running Reverse KL  | 4.16     |
| Running Update Time | 737      |
----------------------------------
-2024-05-14 01:09:35.275724 ʱ-
| Itration            | 738      |
| Loss                | -340     |
| Real Det Return     | -297     |
| Real Sto Return     | -173     |
| Running Env Steps   | 3690000  |
| Running Forward KL  | 23.7     |
| Running Reverse KL  | 3.96     |
| Running Update Time | 738      |
----------------------------------
-2024-05-14 01:12:04.451045 ʱ-
| Itration            | 739      |
| Loss                | -356     |
| Real Det Return     | -355     |
| Real Sto Return     | -189     |
| Running Env Steps   | 3695000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 3.99     |
| Running Update Time | 739      |
----------------------------------
-2024-05-14 01:14:34.366428 ʱ-
| Itration            | 740      |
| Loss                | -402     |
| Real Det Return     | -171     |
| Real Sto Return     | -258     |
| Running Env Steps   | 3700000  |
| Running Forward KL  | 24.3     |
| Running Reverse KL  | 4.54     |
| Running Update Time | 740      |
----------------------------------
-2024-05-14 01:17:03.577279 ʱ-
| Itration            | 741      |
| Loss                | -367     |
| Real Det Return     | -282     |
| Real Sto Return     | -242     |
| Running Env Steps   | 3705000  |
| Running Forward KL  | 24.4     |
| Running Reverse KL  | 3.83     |
| Running Update Time | 741      |
----------------------------------
-2024-05-14 01:19:33.067139 ʱ-
| Itration            | 742      |
| Loss                | -361     |
| Real Det Return     | -499     |
| Real Sto Return     | -265     |
| Running Env Steps   | 3710000  |
| Running Forward KL  | 23.8     |
| Running Reverse KL  | 3.47     |
| Running Update Time | 742      |
----------------------------------
-2024-05-14 01:22:02.247917 ʱ-
| Itration            | 743      |
| Loss                | -331     |
| Real Det Return     | -105     |
| Real Sto Return     | -181     |
| Running Env Steps   | 3715000  |
| Running Forward KL  | 24       |
| Running Reverse KL  | 4.38     |
| Running Update Time | 743      |
----------------------------------
-2024-05-14 01:24:31.533622 ʱ-
| Itration            | 744      |
| Loss                | -361     |
| Real Det Return     | -103     |
| Real Sto Return     | -197     |
| Running Env Steps   | 3720000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 4.02     |
| Running Update Time | 744      |
----------------------------------
-2024-05-14 01:27:01.043738 ʱ-
| Itration            | 745      |
| Loss                | -344     |
| Real Det Return     | -142     |
| Real Sto Return     | -270     |
| Running Env Steps   | 3725000  |
| Running Forward KL  | 24.4     |
| Running Reverse KL  | 4.89     |
| Running Update Time | 745      |
----------------------------------
-2024-05-14 01:29:30.963115 ʱ-
| Itration            | 746      |
| Loss                | -379     |
| Real Det Return     | -355     |
| Real Sto Return     | -183     |
| Running Env Steps   | 3730000  |
| Running Forward KL  | 24       |
| Running Reverse KL  | 3.9      |
| Running Update Time | 746      |
----------------------------------
-2024-05-14 01:32:01.163358 ʱ-
| Itration            | 747      |
| Loss                | -370     |
| Real Det Return     | -275     |
| Real Sto Return     | -188     |
| Running Env Steps   | 3735000  |
| Running Forward KL  | 23.8     |
| Running Reverse KL  | 3.75     |
| Running Update Time | 747      |
----------------------------------
-2024-05-14 01:34:30.353163 ʱ-
| Itration            | 748      |
| Loss                | -334     |
| Real Det Return     | -112     |
| Real Sto Return     | -211     |
| Running Env Steps   | 3740000  |
| Running Forward KL  | 23.7     |
| Running Reverse KL  | 4.14     |
| Running Update Time | 748      |
----------------------------------
-2024-05-14 01:36:59.390478 ʱ-
| Itration            | 749      |
| Loss                | -330     |
| Real Det Return     | -203     |
| Real Sto Return     | -189     |
| Running Env Steps   | 3745000  |
| Running Forward KL  | 24       |
| Running Reverse KL  | 4.53     |
| Running Update Time | 749      |
----------------------------------
-2024-05-14 01:39:29.009745 ʱ-
| Itration            | 750      |
| Loss                | -343     |
| Real Det Return     | -138     |
| Real Sto Return     | -195     |
| Running Env Steps   | 3750000  |
| Running Forward KL  | 23.4     |
| Running Reverse KL  | 3.97     |
| Running Update Time | 750      |
----------------------------------
-2024-05-14 01:41:58.802488 ʱ-
| Itration            | 751      |
| Loss                | -359     |
| Real Det Return     | -105     |
| Real Sto Return     | -200     |
| Running Env Steps   | 3755000  |
| Running Forward KL  | 23.8     |
| Running Reverse KL  | 4.03     |
| Running Update Time | 751      |
----------------------------------
-2024-05-14 01:44:28.135465 ʱ-
| Itration            | 752      |
| Loss                | -356     |
| Real Det Return     | -162     |
| Real Sto Return     | -186     |
| Running Env Steps   | 3760000  |
| Running Forward KL  | 24.2     |
| Running Reverse KL  | 3.85     |
| Running Update Time | 752      |
----------------------------------
-2024-05-14 01:46:57.270752 ʱ-
| Itration            | 753      |
| Loss                | -349     |
| Real Det Return     | -405     |
| Real Sto Return     | -189     |
| Running Env Steps   | 3765000  |
| Running Forward KL  | 23.8     |
| Running Reverse KL  | 4.14     |
| Running Update Time | 753      |
----------------------------------
-2024-05-14 01:49:26.788421 ʱ-
| Itration            | 754      |
| Loss                | -358     |
| Real Det Return     | -111     |
| Real Sto Return     | -206     |
| Running Env Steps   | 3770000  |
| Running Forward KL  | 24.1     |
| Running Reverse KL  | 4.14     |
| Running Update Time | 754      |
----------------------------------
-2024-05-14 01:51:56.388307 ʱ-
| Itration            | 755      |
| Loss                | -341     |
| Real Det Return     | -202     |
| Real Sto Return     | -180     |
| Running Env Steps   | 3775000  |
| Running Forward KL  | 23.8     |
| Running Reverse KL  | 4.03     |
| Running Update Time | 755      |
----------------------------------
-2024-05-14 01:54:25.534987 ʱ-
| Itration            | 756      |
| Loss                | -357     |
| Real Det Return     | -294     |
| Real Sto Return     | -182     |
| Running Env Steps   | 3780000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 3.26     |
| Running Update Time | 756      |
----------------------------------
-2024-05-14 01:56:54.648995 ʱ-
| Itration            | 757      |
| Loss                | -393     |
| Real Det Return     | -181     |
| Real Sto Return     | -174     |
| Running Env Steps   | 3785000  |
| Running Forward KL  | 23.5     |
| Running Reverse KL  | 3.88     |
| Running Update Time | 757      |
----------------------------------
-2024-05-14 01:59:24.108790 ʱ-
| Itration            | 758      |
| Loss                | -347     |
| Real Det Return     | -159     |
| Real Sto Return     | -178     |
| Running Env Steps   | 3790000  |
| Running Forward KL  | 23.5     |
| Running Reverse KL  | 3.92     |
| Running Update Time | 758      |
----------------------------------
-2024-05-14 02:01:53.525499 ʱ-
| Itration            | 759      |
| Loss                | -402     |
| Real Det Return     | -200     |
| Real Sto Return     | -189     |
| Running Env Steps   | 3795000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 3.75     |
| Running Update Time | 759      |
----------------------------------
-2024-05-14 02:04:23.080812 ʱ-
| Itration            | 760      |
| Loss                | -357     |
| Real Det Return     | -258     |
| Real Sto Return     | -184     |
| Running Env Steps   | 3800000  |
| Running Forward KL  | 24.1     |
| Running Reverse KL  | 4.51     |
| Running Update Time | 760      |
----------------------------------
-2024-05-14 02:06:52.663968 ʱ-
| Itration            | 761      |
| Loss                | -355     |
| Real Det Return     | -164     |
| Real Sto Return     | -196     |
| Running Env Steps   | 3805000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 4.38     |
| Running Update Time | 761      |
----------------------------------
-2024-05-14 02:09:22.343058 ʱ-
| Itration            | 762      |
| Loss                | -353     |
| Real Det Return     | -220     |
| Real Sto Return     | -202     |
| Running Env Steps   | 3810000  |
| Running Forward KL  | 23.4     |
| Running Reverse KL  | 4.41     |
| Running Update Time | 762      |
----------------------------------
-2024-05-14 02:11:51.454501 ʱ-
| Itration            | 763      |
| Loss                | -409     |
| Real Det Return     | -116     |
| Real Sto Return     | -195     |
| Running Env Steps   | 3815000  |
| Running Forward KL  | 24.2     |
| Running Reverse KL  | 4.22     |
| Running Update Time | 763      |
----------------------------------
-2024-05-14 02:14:22.450345 ʱ-
| Itration            | 764      |
| Loss                | -348     |
| Real Det Return     | -352     |
| Real Sto Return     | -210     |
| Running Env Steps   | 3820000  |
| Running Forward KL  | 23.4     |
| Running Reverse KL  | 3.66     |
| Running Update Time | 764      |
----------------------------------
-2024-05-14 02:16:51.408597 ʱ-
| Itration            | 765      |
| Loss                | -377     |
| Real Det Return     | -106     |
| Real Sto Return     | -193     |
| Running Env Steps   | 3825000  |
| Running Forward KL  | 24       |
| Running Reverse KL  | 4.54     |
| Running Update Time | 765      |
----------------------------------
-2024-05-14 02:19:21.290038 ʱ-
| Itration            | 766      |
| Loss                | -351     |
| Real Det Return     | -159     |
| Real Sto Return     | -271     |
| Running Env Steps   | 3830000  |
| Running Forward KL  | 23.8     |
| Running Reverse KL  | 4.76     |
| Running Update Time | 766      |
----------------------------------
-2024-05-14 02:21:50.228618 ʱ-
| Itration            | 767      |
| Loss                | -351     |
| Real Det Return     | -186     |
| Real Sto Return     | -173     |
| Running Env Steps   | 3835000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 4.32     |
| Running Update Time | 767      |
----------------------------------
-2024-05-14 02:24:19.800152 ʱ-
| Itration            | 768      |
| Loss                | -360     |
| Real Det Return     | -370     |
| Real Sto Return     | -213     |
| Running Env Steps   | 3840000  |
| Running Forward KL  | 23.4     |
| Running Reverse KL  | 3.81     |
| Running Update Time | 768      |
----------------------------------
-2024-05-14 02:26:49.248245 ʱ-
| Itration            | 769      |
| Loss                | -375     |
| Real Det Return     | -292     |
| Real Sto Return     | -193     |
| Running Env Steps   | 3845000  |
| Running Forward KL  | 23.6     |
| Running Reverse KL  | 4.44     |
| Running Update Time | 769      |
----------------------------------
-2024-05-14 02:29:18.429650 ʱ-
| Itration            | 770      |
| Loss                | -369     |
| Real Det Return     | -364     |
| Real Sto Return     | -215     |
| Running Env Steps   | 3850000  |
| Running Forward KL  | 23.7     |
| Running Reverse KL  | 4        |
| Running Update Time | 770      |
----------------------------------
-2024-05-14 02:31:47.624216 ʱ-
| Itration            | 771      |
| Loss                | -388     |
| Real Det Return     | -385     |
| Real Sto Return     | -280     |
| Running Env Steps   | 3855000  |
| Running Forward KL  | 23.8     |
| Running Reverse KL  | 3.67     |
| Running Update Time | 771      |
----------------------------------
-2024-05-14 02:34:17.695577 ʱ-
| Itration            | 772      |
| Loss                | -369     |
| Real Det Return     | -305     |
| Real Sto Return     | -247     |
| Running Env Steps   | 3860000  |
| Running Forward KL  | 24.1     |
| Running Reverse KL  | 4.02     |
| Running Update Time | 772      |
----------------------------------
-2024-05-14 02:36:47.158910 ʱ-
| Itration            | 773      |
| Loss                | -370     |
| Real Det Return     | -486     |
| Real Sto Return     | -225     |
| Running Env Steps   | 3865000  |
| Running Forward KL  | 23       |
| Running Reverse KL  | 4.18     |
| Running Update Time | 773      |
----------------------------------
-2024-05-14 02:39:17.515240 ʱ-
| Itration            | 774      |
| Loss                | -370     |
| Real Det Return     | -395     |
| Real Sto Return     | -209     |
| Running Env Steps   | 3870000  |
| Running Forward KL  | 22.9     |
| Running Reverse KL  | 3.87     |
| Running Update Time | 774      |
----------------------------------
-2024-05-14 02:41:46.929928 ʱ-
| Itration            | 775      |
| Loss                | -377     |
| Real Det Return     | -496     |
| Real Sto Return     | -248     |
| Running Env Steps   | 3875000  |
| Running Forward KL  | 24.8     |
| Running Reverse KL  | 4.44     |
| Running Update Time | 775      |
----------------------------------
-2024-05-14 02:44:16.217148 ʱ-
| Itration            | 776      |
| Loss                | -403     |
| Real Det Return     | -670     |
| Real Sto Return     | -366     |
| Running Env Steps   | 3880000  |
| Running Forward KL  | 24.6     |
| Running Reverse KL  | 4.39     |
| Running Update Time | 776      |
----------------------------------
-2024-05-14 02:46:45.740311 ʱ-
| Itration            | 777      |
| Loss                | -329     |
| Real Det Return     | -147     |
| Real Sto Return     | -192     |
| Running Env Steps   | 3885000  |
| Running Forward KL  | 23.6     |
| Running Reverse KL  | 4.26     |
| Running Update Time | 777      |
----------------------------------
-2024-05-14 02:49:15.716429 ʱ-
| Itration            | 778      |
| Loss                | -333     |
| Real Det Return     | -320     |
| Real Sto Return     | -197     |
| Running Env Steps   | 3890000  |
| Running Forward KL  | 24.2     |
| Running Reverse KL  | 4.13     |
| Running Update Time | 778      |
----------------------------------
-2024-05-14 02:51:45.428829 ʱ-
| Itration            | 779      |
| Loss                | -399     |
| Real Det Return     | -486     |
| Real Sto Return     | -281     |
| Running Env Steps   | 3895000  |
| Running Forward KL  | 23.5     |
| Running Reverse KL  | 4.16     |
| Running Update Time | 779      |
----------------------------------
-2024-05-14 02:54:15.077823 ʱ-
| Itration            | 780      |
| Loss                | -386     |
| Real Det Return     | -716     |
| Real Sto Return     | -371     |
| Running Env Steps   | 3900000  |
| Running Forward KL  | 23.6     |
| Running Reverse KL  | 3.78     |
| Running Update Time | 780      |
----------------------------------
-2024-05-14 02:56:44.269441 ʱ-
| Itration            | 781      |
| Loss                | -395     |
| Real Det Return     | -416     |
| Real Sto Return     | -196     |
| Running Env Steps   | 3905000  |
| Running Forward KL  | 23.1     |
| Running Reverse KL  | 3.83     |
| Running Update Time | 781      |
----------------------------------
-2024-05-14 02:59:13.946368 ʱ-
| Itration            | 782      |
| Loss                | -387     |
| Real Det Return     | -271     |
| Real Sto Return     | -188     |
| Running Env Steps   | 3910000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 3.8      |
| Running Update Time | 782      |
----------------------------------
-2024-05-14 03:01:43.415899 ʱ-
| Itration            | 783      |
| Loss                | -387     |
| Real Det Return     | -94.6    |
| Real Sto Return     | -201     |
| Running Env Steps   | 3915000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 4.12     |
| Running Update Time | 783      |
----------------------------------
-2024-05-14 03:04:12.176528 ʱ-
| Itration            | 784      |
| Loss                | -378     |
| Real Det Return     | -239     |
| Real Sto Return     | -172     |
| Running Env Steps   | 3920000  |
| Running Forward KL  | 23.4     |
| Running Reverse KL  | 4.08     |
| Running Update Time | 784      |
----------------------------------
-2024-05-14 03:06:41.524767 ʱ-
| Itration            | 785      |
| Loss                | -431     |
| Real Det Return     | -346     |
| Real Sto Return     | -179     |
| Running Env Steps   | 3925000  |
| Running Forward KL  | 23.2     |
| Running Reverse KL  | 3.84     |
| Running Update Time | 785      |
----------------------------------
-2024-05-14 03:09:10.984293 ʱ-
| Itration            | 786      |
| Loss                | -399     |
| Real Det Return     | -389     |
| Real Sto Return     | -212     |
| Running Env Steps   | 3930000  |
| Running Forward KL  | 23.5     |
| Running Reverse KL  | 3.79     |
| Running Update Time | 786      |
----------------------------------
-2024-05-14 03:11:40.238557 ʱ-
| Itration            | 787      |
| Loss                | -374     |
| Real Det Return     | -96.2    |
| Real Sto Return     | -180     |
| Running Env Steps   | 3935000  |
| Running Forward KL  | 23.9     |
| Running Reverse KL  | 4.47     |
| Running Update Time | 787      |
----------------------------------
-2024-05-14 03:14:10.462051 ʱ-
| Itration            | 788      |
| Loss                | -374     |
| Real Det Return     | -343     |
| Real Sto Return     | -198     |
| Running Env Steps   | 3940000  |
| Running Forward KL  | 24       |
| Running Reverse KL  | 4.11     |
| Running Update Time | 788      |
----------------------------------
-2024-05-14 03:16:40.177007 ʱ-
| Itration            | 789      |
| Loss                | -418     |
| Real Det Return     | -425     |
| Real Sto Return     | -190     |
| Running Env Steps   | 3945000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 3.89     |
| Running Update Time | 789      |
----------------------------------
-2024-05-14 03:19:10.523292 ʱ-
| Itration            | 790      |
| Loss                | -367     |
| Real Det Return     | -332     |
| Real Sto Return     | -178     |
| Running Env Steps   | 3950000  |
| Running Forward KL  | 23.2     |
| Running Reverse KL  | 4.29     |
| Running Update Time | 790      |
----------------------------------
-2024-05-14 03:21:40.864597 ʱ-
| Itration            | 791      |
| Loss                | -422     |
| Real Det Return     | -240     |
| Real Sto Return     | -185     |
| Running Env Steps   | 3955000  |
| Running Forward KL  | 23.9     |
| Running Reverse KL  | 3.87     |
| Running Update Time | 791      |
----------------------------------
-2024-05-14 03:24:10.427672 ʱ-
| Itration            | 792      |
| Loss                | -394     |
| Real Det Return     | -84.8    |
| Real Sto Return     | -215     |
| Running Env Steps   | 3960000  |
| Running Forward KL  | 23.6     |
| Running Reverse KL  | 4.5      |
| Running Update Time | 792      |
----------------------------------
-2024-05-14 03:26:40.214928 ʱ-
| Itration            | 793      |
| Loss                | -401     |
| Real Det Return     | -406     |
| Real Sto Return     | -204     |
| Running Env Steps   | 3965000  |
| Running Forward KL  | 23.7     |
| Running Reverse KL  | 3.84     |
| Running Update Time | 793      |
----------------------------------
-2024-05-14 03:29:09.314598 ʱ-
| Itration            | 794      |
| Loss                | -397     |
| Real Det Return     | -216     |
| Real Sto Return     | -225     |
| Running Env Steps   | 3970000  |
| Running Forward KL  | 24.2     |
| Running Reverse KL  | 4.6      |
| Running Update Time | 794      |
----------------------------------
-2024-05-14 03:31:39.320969 ʱ-
| Itration            | 795      |
| Loss                | -382     |
| Real Det Return     | -287     |
| Real Sto Return     | -196     |
| Running Env Steps   | 3975000  |
| Running Forward KL  | 23.8     |
| Running Reverse KL  | 4.01     |
| Running Update Time | 795      |
----------------------------------
-2024-05-14 03:34:09.340963 ʱ-
| Itration            | 796      |
| Loss                | -428     |
| Real Det Return     | -186     |
| Real Sto Return     | -287     |
| Running Env Steps   | 3980000  |
| Running Forward KL  | 24.2     |
| Running Reverse KL  | 5.08     |
| Running Update Time | 796      |
----------------------------------
-2024-05-14 03:36:39.560250 ʱ-
| Itration            | 797      |
| Loss                | -385     |
| Real Det Return     | -151     |
| Real Sto Return     | -228     |
| Running Env Steps   | 3985000  |
| Running Forward KL  | 23.5     |
| Running Reverse KL  | 4.49     |
| Running Update Time | 797      |
----------------------------------
-2024-05-14 03:39:09.277972 ʱ-
| Itration            | 798      |
| Loss                | -391     |
| Real Det Return     | -304     |
| Real Sto Return     | -198     |
| Running Env Steps   | 3990000  |
| Running Forward KL  | 23.8     |
| Running Reverse KL  | 4.02     |
| Running Update Time | 798      |
----------------------------------
-2024-05-14 03:41:39.241671 ʱ-
| Itration            | 799      |
| Loss                | -370     |
| Real Det Return     | -112     |
| Real Sto Return     | -175     |
| Running Env Steps   | 3995000  |
| Running Forward KL  | 23.1     |
| Running Reverse KL  | 3.9      |
| Running Update Time | 799      |
----------------------------------
-2024-05-14 03:44:08.906347 ʱ-
| Itration            | 800      |
| Loss                | -407     |
| Real Det Return     | -253     |
| Real Sto Return     | -183     |
| Running Env Steps   | 4000000  |
| Running Forward KL  | 22.7     |
| Running Reverse KL  | 3.99     |
| Running Update Time | 800      |
----------------------------------
-2024-05-14 03:46:38.503978 ʱ-
| Itration            | 801      |
| Loss                | -369     |
| Real Det Return     | -127     |
| Real Sto Return     | -190     |
| Running Env Steps   | 4005000  |
| Running Forward KL  | 23.6     |
| Running Reverse KL  | 4.16     |
| Running Update Time | 801      |
----------------------------------
-2024-05-14 03:49:08.166905 ʱ-
| Itration            | 802      |
| Loss                | -383     |
| Real Det Return     | -595     |
| Real Sto Return     | -309     |
| Running Env Steps   | 4010000  |
| Running Forward KL  | 24       |
| Running Reverse KL  | 4.27     |
| Running Update Time | 802      |
----------------------------------
-2024-05-14 03:51:37.825789 ʱ-
| Itration            | 803      |
| Loss                | -390     |
| Real Det Return     | -224     |
| Real Sto Return     | -196     |
| Running Env Steps   | 4015000  |
| Running Forward KL  | 23       |
| Running Reverse KL  | 3.93     |
| Running Update Time | 803      |
----------------------------------
-2024-05-14 03:54:06.969374 ʱ-
| Itration            | 804      |
| Loss                | -375     |
| Real Det Return     | -169     |
| Real Sto Return     | -177     |
| Running Env Steps   | 4020000  |
| Running Forward KL  | 22.8     |
| Running Reverse KL  | 3.91     |
| Running Update Time | 804      |
----------------------------------
-2024-05-14 03:56:36.362069 ʱ-
| Itration            | 805      |
| Loss                | -392     |
| Real Det Return     | -384     |
| Real Sto Return     | -217     |
| Running Env Steps   | 4025000  |
| Running Forward KL  | 23.4     |
| Running Reverse KL  | 3.92     |
| Running Update Time | 805      |
----------------------------------
-2024-05-14 03:59:05.805782 ʱ-
| Itration            | 806      |
| Loss                | -406     |
| Real Det Return     | -408     |
| Real Sto Return     | -229     |
| Running Env Steps   | 4030000  |
| Running Forward KL  | 23.2     |
| Running Reverse KL  | 4.06     |
| Running Update Time | 806      |
----------------------------------
-2024-05-14 04:01:35.047833 ʱ-
| Itration            | 807      |
| Loss                | -386     |
| Real Det Return     | -450     |
| Real Sto Return     | -244     |
| Running Env Steps   | 4035000  |
| Running Forward KL  | 23.1     |
| Running Reverse KL  | 4.07     |
| Running Update Time | 807      |
----------------------------------
-2024-05-14 04:04:04.317819 ʱ-
| Itration            | 808      |
| Loss                | -363     |
| Real Det Return     | -116     |
| Real Sto Return     | -189     |
| Running Env Steps   | 4040000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 4.66     |
| Running Update Time | 808      |
----------------------------------
-2024-05-14 04:06:33.982750 ʱ-
| Itration            | 809      |
| Loss                | -380     |
| Real Det Return     | -133     |
| Real Sto Return     | -220     |
| Running Env Steps   | 4045000  |
| Running Forward KL  | 23       |
| Running Reverse KL  | 3.67     |
| Running Update Time | 809      |
----------------------------------
-2024-05-14 04:09:03.237370 ʱ-
| Itration            | 810      |
| Loss                | -392     |
| Real Det Return     | -422     |
| Real Sto Return     | -197     |
| Running Env Steps   | 4050000  |
| Running Forward KL  | 23.7     |
| Running Reverse KL  | 4.53     |
| Running Update Time | 810      |
----------------------------------
-2024-05-14 04:11:33.134185 ʱ-
| Itration            | 811      |
| Loss                | -403     |
| Real Det Return     | -255     |
| Real Sto Return     | -176     |
| Running Env Steps   | 4055000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 3.85     |
| Running Update Time | 811      |
----------------------------------
-2024-05-14 04:14:02.742390 ʱ-
| Itration            | 812      |
| Loss                | -384     |
| Real Det Return     | -257     |
| Real Sto Return     | -195     |
| Running Env Steps   | 4060000  |
| Running Forward KL  | 23.5     |
| Running Reverse KL  | 4.31     |
| Running Update Time | 812      |
----------------------------------
-2024-05-14 04:16:32.012962 ʱ-
| Itration            | 813      |
| Loss                | -412     |
| Real Det Return     | -195     |
| Real Sto Return     | -187     |
| Running Env Steps   | 4065000  |
| Running Forward KL  | 23.1     |
| Running Reverse KL  | 4.02     |
| Running Update Time | 813      |
----------------------------------
-2024-05-14 04:19:01.554199 ʱ-
| Itration            | 814      |
| Loss                | -379     |
| Real Det Return     | -168     |
| Real Sto Return     | -183     |
| Running Env Steps   | 4070000  |
| Running Forward KL  | 23.7     |
| Running Reverse KL  | 5.41     |
| Running Update Time | 814      |
----------------------------------
-2024-05-14 04:21:31.197006 ʱ-
| Itration            | 815      |
| Loss                | -389     |
| Real Det Return     | -344     |
| Real Sto Return     | -192     |
| Running Env Steps   | 4075000  |
| Running Forward KL  | 24.1     |
| Running Reverse KL  | 4.25     |
| Running Update Time | 815      |
----------------------------------
-2024-05-14 04:24:01.119769 ʱ-
| Itration            | 816      |
| Loss                | -371     |
| Real Det Return     | -365     |
| Real Sto Return     | -207     |
| Running Env Steps   | 4080000  |
| Running Forward KL  | 22.7     |
| Running Reverse KL  | 4.03     |
| Running Update Time | 816      |
----------------------------------
-2024-05-14 04:26:30.064378 ʱ-
| Itration            | 817      |
| Loss                | -405     |
| Real Det Return     | -131     |
| Real Sto Return     | -181     |
| Running Env Steps   | 4085000  |
| Running Forward KL  | 22.6     |
| Running Reverse KL  | 3.97     |
| Running Update Time | 817      |
----------------------------------
-2024-05-14 04:28:59.364029 ʱ-
| Itration            | 818      |
| Loss                | -412     |
| Real Det Return     | -138     |
| Real Sto Return     | -196     |
| Running Env Steps   | 4090000  |
| Running Forward KL  | 23.5     |
| Running Reverse KL  | 4.19     |
| Running Update Time | 818      |
----------------------------------
-2024-05-14 04:31:28.861865 ʱ-
| Itration            | 819      |
| Loss                | -404     |
| Real Det Return     | -412     |
| Real Sto Return     | -214     |
| Running Env Steps   | 4095000  |
| Running Forward KL  | 22.9     |
| Running Reverse KL  | 3.32     |
| Running Update Time | 819      |
----------------------------------
-2024-05-14 04:33:58.547044 ʱ-
| Itration            | 820      |
| Loss                | -425     |
| Real Det Return     | -164     |
| Real Sto Return     | -166     |
| Running Env Steps   | 4100000  |
| Running Forward KL  | 23.8     |
| Running Reverse KL  | 4.99     |
| Running Update Time | 820      |
----------------------------------
-2024-05-14 04:36:28.045192 ʱ-
| Itration            | 821      |
| Loss                | -438     |
| Real Det Return     | -185     |
| Real Sto Return     | -179     |
| Running Env Steps   | 4105000  |
| Running Forward KL  | 23.1     |
| Running Reverse KL  | 4.03     |
| Running Update Time | 821      |
----------------------------------
-2024-05-14 04:38:57.290310 ʱ-
| Itration            | 822      |
| Loss                | -416     |
| Real Det Return     | -296     |
| Real Sto Return     | -203     |
| Running Env Steps   | 4110000  |
| Running Forward KL  | 23.4     |
| Running Reverse KL  | 4.47     |
| Running Update Time | 822      |
----------------------------------
-2024-05-14 04:41:26.706689 ʱ-
| Itration            | 823      |
| Loss                | -404     |
| Real Det Return     | -97.5    |
| Real Sto Return     | -202     |
| Running Env Steps   | 4115000  |
| Running Forward KL  | 23.4     |
| Running Reverse KL  | 4.84     |
| Running Update Time | 823      |
----------------------------------
-2024-05-14 04:43:55.652742 ʱ-
| Itration            | 824      |
| Loss                | -385     |
| Real Det Return     | -123     |
| Real Sto Return     | -170     |
| Running Env Steps   | 4120000  |
| Running Forward KL  | 22.5     |
| Running Reverse KL  | 4.12     |
| Running Update Time | 824      |
----------------------------------
-2024-05-14 04:46:25.375067 ʱ-
| Itration            | 825      |
| Loss                | -378     |
| Real Det Return     | -149     |
| Real Sto Return     | -198     |
| Running Env Steps   | 4125000  |
| Running Forward KL  | 23.4     |
| Running Reverse KL  | 4.61     |
| Running Update Time | 825      |
----------------------------------
-2024-05-14 04:48:54.174164 ʱ-
| Itration            | 826      |
| Loss                | -443     |
| Real Det Return     | -274     |
| Real Sto Return     | -210     |
| Running Env Steps   | 4130000  |
| Running Forward KL  | 22.4     |
| Running Reverse KL  | 3.25     |
| Running Update Time | 826      |
----------------------------------
-2024-05-14 04:51:23.944596 ʱ-
| Itration            | 827      |
| Loss                | -403     |
| Real Det Return     | -238     |
| Real Sto Return     | -179     |
| Running Env Steps   | 4135000  |
| Running Forward KL  | 23.8     |
| Running Reverse KL  | 4.49     |
| Running Update Time | 827      |
----------------------------------
-2024-05-14 04:53:53.407951 ʱ-
| Itration            | 828      |
| Loss                | -411     |
| Real Det Return     | -103     |
| Real Sto Return     | -179     |
| Running Env Steps   | 4140000  |
| Running Forward KL  | 23       |
| Running Reverse KL  | 3.96     |
| Running Update Time | 828      |
----------------------------------
-2024-05-14 04:56:22.554787 ʱ-
| Itration            | 829      |
| Loss                | -447     |
| Real Det Return     | -437     |
| Real Sto Return     | -204     |
| Running Env Steps   | 4145000  |
| Running Forward KL  | 23.5     |
| Running Reverse KL  | 4.39     |
| Running Update Time | 829      |
----------------------------------
-2024-05-14 04:58:52.231837 ʱ-
| Itration            | 830      |
| Loss                | -357     |
| Real Det Return     | -241     |
| Real Sto Return     | -171     |
| Running Env Steps   | 4150000  |
| Running Forward KL  | 22.6     |
| Running Reverse KL  | 4.38     |
| Running Update Time | 830      |
----------------------------------
-2024-05-14 05:01:21.707943 ʱ-
| Itration            | 831      |
| Loss                | -407     |
| Real Det Return     | -246     |
| Real Sto Return     | -217     |
| Running Env Steps   | 4155000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 4.28     |
| Running Update Time | 831      |
----------------------------------
-2024-05-14 05:03:51.342847 ʱ-
| Itration            | 832      |
| Loss                | -421     |
| Real Det Return     | -182     |
| Real Sto Return     | -170     |
| Running Env Steps   | 4160000  |
| Running Forward KL  | 23.4     |
| Running Reverse KL  | 3.76     |
| Running Update Time | 832      |
----------------------------------
-2024-05-14 05:06:21.278797 ʱ-
| Itration            | 833      |
| Loss                | -403     |
| Real Det Return     | -216     |
| Real Sto Return     | -188     |
| Running Env Steps   | 4165000  |
| Running Forward KL  | 22.4     |
| Running Reverse KL  | 3.8      |
| Running Update Time | 833      |
----------------------------------
-2024-05-14 05:08:51.042138 ʱ-
| Itration            | 834      |
| Loss                | -409     |
| Real Det Return     | -190     |
| Real Sto Return     | -167     |
| Running Env Steps   | 4170000  |
| Running Forward KL  | 22.6     |
| Running Reverse KL  | 4.4      |
| Running Update Time | 834      |
----------------------------------
-2024-05-14 05:11:20.806172 ʱ-
| Itration            | 835      |
| Loss                | -420     |
| Real Det Return     | -500     |
| Real Sto Return     | -237     |
| Running Env Steps   | 4175000  |
| Running Forward KL  | 23.9     |
| Running Reverse KL  | 3.85     |
| Running Update Time | 835      |
----------------------------------
-2024-05-14 05:13:50.809552 ʱ-
| Itration            | 836      |
| Loss                | -452     |
| Real Det Return     | -468     |
| Real Sto Return     | -253     |
| Running Env Steps   | 4180000  |
| Running Forward KL  | 23.6     |
| Running Reverse KL  | 4.96     |
| Running Update Time | 836      |
----------------------------------
-2024-05-14 05:16:20.428051 ʱ-
| Itration            | 837      |
| Loss                | -440     |
| Real Det Return     | -430     |
| Real Sto Return     | -189     |
| Running Env Steps   | 4185000  |
| Running Forward KL  | 23.6     |
| Running Reverse KL  | 4.12     |
| Running Update Time | 837      |
----------------------------------
-2024-05-14 05:18:50.737770 ʱ-
| Itration            | 838      |
| Loss                | -409     |
| Real Det Return     | -371     |
| Real Sto Return     | -201     |
| Running Env Steps   | 4190000  |
| Running Forward KL  | 23.1     |
| Running Reverse KL  | 4.15     |
| Running Update Time | 838      |
----------------------------------
-2024-05-14 05:21:20.735439 ʱ-
| Itration            | 839      |
| Loss                | -396     |
| Real Det Return     | -293     |
| Real Sto Return     | -200     |
| Running Env Steps   | 4195000  |
| Running Forward KL  | 23       |
| Running Reverse KL  | 4.29     |
| Running Update Time | 839      |
----------------------------------
-2024-05-14 05:23:49.758754 ʱ-
| Itration            | 840      |
| Loss                | -489     |
| Real Det Return     | -99.5    |
| Real Sto Return     | -182     |
| Running Env Steps   | 4200000  |
| Running Forward KL  | 23.6     |
| Running Reverse KL  | 4.62     |
| Running Update Time | 840      |
----------------------------------
-2024-05-14 05:26:18.731094 ʱ-
| Itration            | 841      |
| Loss                | -424     |
| Real Det Return     | -314     |
| Real Sto Return     | -230     |
| Running Env Steps   | 4205000  |
| Running Forward KL  | 23.4     |
| Running Reverse KL  | 4.47     |
| Running Update Time | 841      |
----------------------------------
-2024-05-14 05:28:47.640915 ʱ-
| Itration            | 842      |
| Loss                | -385     |
| Real Det Return     | -122     |
| Real Sto Return     | -195     |
| Running Env Steps   | 4210000  |
| Running Forward KL  | 23       |
| Running Reverse KL  | 3.97     |
| Running Update Time | 842      |
----------------------------------
-2024-05-14 05:31:17.265418 ʱ-
| Itration            | 843      |
| Loss                | -403     |
| Real Det Return     | -213     |
| Real Sto Return     | -185     |
| Running Env Steps   | 4215000  |
| Running Forward KL  | 22.2     |
| Running Reverse KL  | 3.55     |
| Running Update Time | 843      |
----------------------------------
-2024-05-14 05:33:46.635682 ʱ-
| Itration            | 844      |
| Loss                | -427     |
| Real Det Return     | -142     |
| Real Sto Return     | -227     |
| Running Env Steps   | 4220000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 4.09     |
| Running Update Time | 844      |
----------------------------------
-2024-05-14 05:36:16.057996 ʱ-
| Itration            | 845      |
| Loss                | -431     |
| Real Det Return     | -124     |
| Real Sto Return     | -216     |
| Running Env Steps   | 4225000  |
| Running Forward KL  | 23.1     |
| Running Reverse KL  | 4.69     |
| Running Update Time | 845      |
----------------------------------
-2024-05-14 05:38:45.808659 ʱ-
| Itration            | 846      |
| Loss                | -453     |
| Real Det Return     | -123     |
| Real Sto Return     | -200     |
| Running Env Steps   | 4230000  |
| Running Forward KL  | 22.9     |
| Running Reverse KL  | 4.36     |
| Running Update Time | 846      |
----------------------------------
-2024-05-14 05:41:15.414393 ʱ-
| Itration            | 847      |
| Loss                | -429     |
| Real Det Return     | -125     |
| Real Sto Return     | -222     |
| Running Env Steps   | 4235000  |
| Running Forward KL  | 23.2     |
| Running Reverse KL  | 5.12     |
| Running Update Time | 847      |
----------------------------------
-2024-05-14 05:43:44.624704 ʱ-
| Itration            | 848      |
| Loss                | -441     |
| Real Det Return     | -197     |
| Real Sto Return     | -227     |
| Running Env Steps   | 4240000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 4.66     |
| Running Update Time | 848      |
----------------------------------
-2024-05-14 05:46:13.719615 ʱ-
| Itration            | 849      |
| Loss                | -421     |
| Real Det Return     | -249     |
| Real Sto Return     | -188     |
| Running Env Steps   | 4245000  |
| Running Forward KL  | 22.5     |
| Running Reverse KL  | 4        |
| Running Update Time | 849      |
----------------------------------
-2024-05-14 05:48:43.666287 ʱ-
| Itration            | 850      |
| Loss                | -447     |
| Real Det Return     | -331     |
| Real Sto Return     | -200     |
| Running Env Steps   | 4250000  |
| Running Forward KL  | 23.5     |
| Running Reverse KL  | 4.38     |
| Running Update Time | 850      |
----------------------------------
-2024-05-14 05:51:13.107866 ʱ-
| Itration            | 851      |
| Loss                | -421     |
| Real Det Return     | -179     |
| Real Sto Return     | -206     |
| Running Env Steps   | 4255000  |
| Running Forward KL  | 22.6     |
| Running Reverse KL  | 3.84     |
| Running Update Time | 851      |
----------------------------------
-2024-05-14 05:53:42.791862 ʱ-
| Itration            | 852      |
| Loss                | -446     |
| Real Det Return     | -201     |
| Real Sto Return     | -221     |
| Running Env Steps   | 4260000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 4.53     |
| Running Update Time | 852      |
----------------------------------
-2024-05-14 05:56:12.791713 ʱ-
| Itration            | 853      |
| Loss                | -426     |
| Real Det Return     | -233     |
| Real Sto Return     | -185     |
| Running Env Steps   | 4265000  |
| Running Forward KL  | 22.8     |
| Running Reverse KL  | 4.55     |
| Running Update Time | 853      |
----------------------------------
-2024-05-14 05:58:42.248690 ʱ-
| Itration            | 854      |
| Loss                | -429     |
| Real Det Return     | -367     |
| Real Sto Return     | -220     |
| Running Env Steps   | 4270000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 4.25     |
| Running Update Time | 854      |
----------------------------------
-2024-05-14 06:01:11.677403 ʱ-
| Itration            | 855      |
| Loss                | -456     |
| Real Det Return     | -325     |
| Real Sto Return     | -201     |
| Running Env Steps   | 4275000  |
| Running Forward KL  | 22.9     |
| Running Reverse KL  | 4.16     |
| Running Update Time | 855      |
----------------------------------
-2024-05-14 06:03:41.120532 ʱ-
| Itration            | 856      |
| Loss                | -460     |
| Real Det Return     | -491     |
| Real Sto Return     | -208     |
| Running Env Steps   | 4280000  |
| Running Forward KL  | 22.6     |
| Running Reverse KL  | 4.03     |
| Running Update Time | 856      |
----------------------------------
-2024-05-14 06:06:10.484897 ʱ-
| Itration            | 857      |
| Loss                | -414     |
| Real Det Return     | -151     |
| Real Sto Return     | -242     |
| Running Env Steps   | 4285000  |
| Running Forward KL  | 23.4     |
| Running Reverse KL  | 4.46     |
| Running Update Time | 857      |
----------------------------------
-2024-05-14 06:08:39.756400 ʱ-
| Itration            | 858      |
| Loss                | -454     |
| Real Det Return     | -562     |
| Real Sto Return     | -278     |
| Running Env Steps   | 4290000  |
| Running Forward KL  | 22.8     |
| Running Reverse KL  | 4.35     |
| Running Update Time | 858      |
----------------------------------
-2024-05-14 06:11:09.160234 ʱ-
| Itration            | 859      |
| Loss                | -444     |
| Real Det Return     | -350     |
| Real Sto Return     | -239     |
| Running Env Steps   | 4295000  |
| Running Forward KL  | 23       |
| Running Reverse KL  | 4.61     |
| Running Update Time | 859      |
----------------------------------
-2024-05-14 06:13:38.509447 ʱ-
| Itration            | 860      |
| Loss                | -466     |
| Real Det Return     | -121     |
| Real Sto Return     | -176     |
| Running Env Steps   | 4300000  |
| Running Forward KL  | 23       |
| Running Reverse KL  | 4.47     |
| Running Update Time | 860      |
----------------------------------
-2024-05-14 06:16:08.127348 ʱ-
| Itration            | 861      |
| Loss                | -463     |
| Real Det Return     | -330     |
| Real Sto Return     | -204     |
| Running Env Steps   | 4305000  |
| Running Forward KL  | 22.6     |
| Running Reverse KL  | 4.66     |
| Running Update Time | 861      |
----------------------------------
-2024-05-14 06:18:37.801140 ʱ-
| Itration            | 862      |
| Loss                | -444     |
| Real Det Return     | -174     |
| Real Sto Return     | -195     |
| Running Env Steps   | 4310000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 4.68     |
| Running Update Time | 862      |
----------------------------------
-2024-05-14 06:21:07.413171 ʱ-
| Itration            | 863      |
| Loss                | -460     |
| Real Det Return     | -261     |
| Real Sto Return     | -227     |
| Running Env Steps   | 4315000  |
| Running Forward KL  | 22.9     |
| Running Reverse KL  | 4.23     |
| Running Update Time | 863      |
----------------------------------
-2024-05-14 06:23:37.370983 ʱ-
| Itration            | 864      |
| Loss                | -482     |
| Real Det Return     | -156     |
| Real Sto Return     | -178     |
| Running Env Steps   | 4320000  |
| Running Forward KL  | 23       |
| Running Reverse KL  | 4.41     |
| Running Update Time | 864      |
----------------------------------
-2024-05-14 06:26:06.769813 ʱ-
| Itration            | 865      |
| Loss                | -485     |
| Real Det Return     | -276     |
| Real Sto Return     | -174     |
| Running Env Steps   | 4325000  |
| Running Forward KL  | 22.6     |
| Running Reverse KL  | 4.22     |
| Running Update Time | 865      |
----------------------------------
-2024-05-14 06:28:36.055358 ʱ-
| Itration            | 866      |
| Loss                | -441     |
| Real Det Return     | -239     |
| Real Sto Return     | -174     |
| Running Env Steps   | 4330000  |
| Running Forward KL  | 23.1     |
| Running Reverse KL  | 4.57     |
| Running Update Time | 866      |
----------------------------------
-2024-05-14 06:31:08.626431 ʱ-
| Itration            | 867      |
| Loss                | -425     |
| Real Det Return     | -130     |
| Real Sto Return     | -171     |
| Running Env Steps   | 4335000  |
| Running Forward KL  | 22.8     |
| Running Reverse KL  | 4.42     |
| Running Update Time | 867      |
----------------------------------
-2024-05-14 06:33:38.322062 ʱ-
| Itration            | 868      |
| Loss                | -462     |
| Real Det Return     | -104     |
| Real Sto Return     | -186     |
| Running Env Steps   | 4340000  |
| Running Forward KL  | 23.2     |
| Running Reverse KL  | 4.66     |
| Running Update Time | 868      |
----------------------------------
-2024-05-14 06:36:08.391974 ʱ-
| Itration            | 869      |
| Loss                | -433     |
| Real Det Return     | -250     |
| Real Sto Return     | -174     |
| Running Env Steps   | 4345000  |
| Running Forward KL  | 22.8     |
| Running Reverse KL  | 4.52     |
| Running Update Time | 869      |
----------------------------------
-2024-05-14 06:38:37.611299 ʱ-
| Itration            | 870      |
| Loss                | -430     |
| Real Det Return     | -127     |
| Real Sto Return     | -179     |
| Running Env Steps   | 4350000  |
| Running Forward KL  | 23       |
| Running Reverse KL  | 4.5      |
| Running Update Time | 870      |
----------------------------------
-2024-05-14 06:41:06.830161 ʱ-
| Itration            | 871      |
| Loss                | -421     |
| Real Det Return     | -215     |
| Real Sto Return     | -217     |
| Running Env Steps   | 4355000  |
| Running Forward KL  | 23.5     |
| Running Reverse KL  | 4.56     |
| Running Update Time | 871      |
----------------------------------
-2024-05-14 06:43:36.079592 ʱ-
| Itration            | 872      |
| Loss                | -444     |
| Real Det Return     | -326     |
| Real Sto Return     | -171     |
| Running Env Steps   | 4360000  |
| Running Forward KL  | 22.9     |
| Running Reverse KL  | 4.12     |
| Running Update Time | 872      |
----------------------------------
-2024-05-14 06:46:05.206979 ʱ-
| Itration            | 873      |
| Loss                | -468     |
| Real Det Return     | -195     |
| Real Sto Return     | -178     |
| Running Env Steps   | 4365000  |
| Running Forward KL  | 22.2     |
| Running Reverse KL  | 3.73     |
| Running Update Time | 873      |
----------------------------------
-2024-05-14 06:48:34.307201 ʱ-
| Itration            | 874      |
| Loss                | -452     |
| Real Det Return     | -101     |
| Real Sto Return     | -196     |
| Running Env Steps   | 4370000  |
| Running Forward KL  | 23.5     |
| Running Reverse KL  | 5.02     |
| Running Update Time | 874      |
----------------------------------
-2024-05-14 06:51:03.905954 ʱ-
| Itration            | 875      |
| Loss                | -446     |
| Real Det Return     | -226     |
| Real Sto Return     | -178     |
| Running Env Steps   | 4375000  |
| Running Forward KL  | 22.6     |
| Running Reverse KL  | 4.26     |
| Running Update Time | 875      |
----------------------------------
-2024-05-14 06:53:33.206656 ʱ-
| Itration            | 876      |
| Loss                | -472     |
| Real Det Return     | -484     |
| Real Sto Return     | -256     |
| Running Env Steps   | 4380000  |
| Running Forward KL  | 22.7     |
| Running Reverse KL  | 4.4      |
| Running Update Time | 876      |
----------------------------------
-2024-05-14 06:56:02.392848 ʱ-
| Itration            | 877      |
| Loss                | -480     |
| Real Det Return     | -192     |
| Real Sto Return     | -187     |
| Running Env Steps   | 4385000  |
| Running Forward KL  | 22.5     |
| Running Reverse KL  | 3.77     |
| Running Update Time | 877      |
----------------------------------
-2024-05-14 06:58:32.364037 ʱ-
| Itration            | 878      |
| Loss                | -424     |
| Real Det Return     | -167     |
| Real Sto Return     | -169     |
| Running Env Steps   | 4390000  |
| Running Forward KL  | 22.4     |
| Running Reverse KL  | 4.29     |
| Running Update Time | 878      |
----------------------------------
-2024-05-14 07:01:01.682190 ʱ-
| Itration            | 879      |
| Loss                | -414     |
| Real Det Return     | -180     |
| Real Sto Return     | -162     |
| Running Env Steps   | 4395000  |
| Running Forward KL  | 22.6     |
| Running Reverse KL  | 4.4      |
| Running Update Time | 879      |
----------------------------------
-2024-05-14 07:03:30.606796 ʱ-
| Itration            | 880      |
| Loss                | -432     |
| Real Det Return     | -244     |
| Real Sto Return     | -170     |
| Running Env Steps   | 4400000  |
| Running Forward KL  | 22.4     |
| Running Reverse KL  | 4.01     |
| Running Update Time | 880      |
----------------------------------
-2024-05-14 07:05:59.699965 ʱ-
| Itration            | 881      |
| Loss                | -472     |
| Real Det Return     | -107     |
| Real Sto Return     | -181     |
| Running Env Steps   | 4405000  |
| Running Forward KL  | 23.2     |
| Running Reverse KL  | 4.96     |
| Running Update Time | 881      |
----------------------------------
-2024-05-14 07:08:28.417381 ʱ-
| Itration            | 882      |
| Loss                | -448     |
| Real Det Return     | -331     |
| Real Sto Return     | -188     |
| Running Env Steps   | 4410000  |
| Running Forward KL  | 22.9     |
| Running Reverse KL  | 4.32     |
| Running Update Time | 882      |
----------------------------------
-2024-05-14 07:10:57.463904 ʱ-
| Itration            | 883      |
| Loss                | -457     |
| Real Det Return     | -155     |
| Real Sto Return     | -172     |
| Running Env Steps   | 4415000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 5.04     |
| Running Update Time | 883      |
----------------------------------
-2024-05-14 07:13:27.187670 ʱ-
| Itration            | 884      |
| Loss                | -473     |
| Real Det Return     | -120     |
| Real Sto Return     | -166     |
| Running Env Steps   | 4420000  |
| Running Forward KL  | 22.5     |
| Running Reverse KL  | 4.34     |
| Running Update Time | 884      |
----------------------------------
-2024-05-14 07:15:56.547105 ʱ-
| Itration            | 885      |
| Loss                | -489     |
| Real Det Return     | -187     |
| Real Sto Return     | -150     |
| Running Env Steps   | 4425000  |
| Running Forward KL  | 22.8     |
| Running Reverse KL  | 4.28     |
| Running Update Time | 885      |
----------------------------------
-2024-05-14 07:18:26.160020 ʱ-
| Itration            | 886      |
| Loss                | -479     |
| Real Det Return     | -279     |
| Real Sto Return     | -167     |
| Running Env Steps   | 4430000  |
| Running Forward KL  | 22.3     |
| Running Reverse KL  | 4.14     |
| Running Update Time | 886      |
----------------------------------
-2024-05-14 07:20:56.057435 ʱ-
| Itration            | 887      |
| Loss                | -492     |
| Real Det Return     | -214     |
| Real Sto Return     | -178     |
| Running Env Steps   | 4435000  |
| Running Forward KL  | 22.7     |
| Running Reverse KL  | 4.26     |
| Running Update Time | 887      |
----------------------------------
-2024-05-14 07:23:25.544800 ʱ-
| Itration            | 888      |
| Loss                | -517     |
| Real Det Return     | -275     |
| Real Sto Return     | -169     |
| Running Env Steps   | 4440000  |
| Running Forward KL  | 22.7     |
| Running Reverse KL  | 4.78     |
| Running Update Time | 888      |
----------------------------------
-2024-05-14 07:25:54.873432 ʱ-
| Itration            | 889      |
| Loss                | -487     |
| Real Det Return     | -433     |
| Real Sto Return     | -212     |
| Running Env Steps   | 4445000  |
| Running Forward KL  | 22.9     |
| Running Reverse KL  | 4.65     |
| Running Update Time | 889      |
----------------------------------
-2024-05-14 07:28:24.491097 ʱ-
| Itration            | 890      |
| Loss                | -476     |
| Real Det Return     | -200     |
| Real Sto Return     | -197     |
| Running Env Steps   | 4450000  |
| Running Forward KL  | 22.8     |
| Running Reverse KL  | 4.64     |
| Running Update Time | 890      |
----------------------------------
-2024-05-14 07:30:54.209723 ʱ-
| Itration            | 891      |
| Loss                | -486     |
| Real Det Return     | -243     |
| Real Sto Return     | -172     |
| Running Env Steps   | 4455000  |
| Running Forward KL  | 23       |
| Running Reverse KL  | 4.51     |
| Running Update Time | 891      |
----------------------------------
-2024-05-14 07:33:24.292879 ʱ-
| Itration            | 892      |
| Loss                | -470     |
| Real Det Return     | -202     |
| Real Sto Return     | -166     |
| Running Env Steps   | 4460000  |
| Running Forward KL  | 22.6     |
| Running Reverse KL  | 4.52     |
| Running Update Time | 892      |
----------------------------------
-2024-05-14 07:35:54.163962 ʱ-
| Itration            | 893      |
| Loss                | -451     |
| Real Det Return     | -96      |
| Real Sto Return     | -175     |
| Running Env Steps   | 4465000  |
| Running Forward KL  | 22.5     |
| Running Reverse KL  | 4.16     |
| Running Update Time | 893      |
----------------------------------
-2024-05-14 07:38:23.494915 ʱ-
| Itration            | 894      |
| Loss                | -477     |
| Real Det Return     | -213     |
| Real Sto Return     | -204     |
| Running Env Steps   | 4470000  |
| Running Forward KL  | 22.9     |
| Running Reverse KL  | 4.51     |
| Running Update Time | 894      |
----------------------------------
-2024-05-14 07:40:53.905342 ʱ-
| Itration            | 895      |
| Loss                | -499     |
| Real Det Return     | -125     |
| Real Sto Return     | -189     |
| Running Env Steps   | 4475000  |
| Running Forward KL  | 22.6     |
| Running Reverse KL  | 4.04     |
| Running Update Time | 895      |
----------------------------------
-2024-05-14 07:43:24.127921 ʱ-
| Itration            | 896      |
| Loss                | -453     |
| Real Det Return     | -128     |
| Real Sto Return     | -182     |
| Running Env Steps   | 4480000  |
| Running Forward KL  | 22       |
| Running Reverse KL  | 4.3      |
| Running Update Time | 896      |
----------------------------------
-2024-05-14 07:45:53.601007 ʱ-
| Itration            | 897      |
| Loss                | -443     |
| Real Det Return     | -89.9    |
| Real Sto Return     | -199     |
| Running Env Steps   | 4485000  |
| Running Forward KL  | 22.2     |
| Running Reverse KL  | 4.76     |
| Running Update Time | 897      |
----------------------------------
-2024-05-14 07:48:23.835720 ʱ-
| Itration            | 898      |
| Loss                | -473     |
| Real Det Return     | -203     |
| Real Sto Return     | -151     |
| Running Env Steps   | 4490000  |
| Running Forward KL  | 21.6     |
| Running Reverse KL  | 3.96     |
| Running Update Time | 898      |
----------------------------------
-2024-05-14 07:50:53.466895 ʱ-
| Itration            | 899      |
| Loss                | -481     |
| Real Det Return     | -142     |
| Real Sto Return     | -160     |
| Running Env Steps   | 4495000  |
| Running Forward KL  | 22.3     |
| Running Reverse KL  | 4.47     |
| Running Update Time | 899      |
----------------------------------
-2024-05-14 07:53:23.608553 ʱ-
| Itration            | 900      |
| Loss                | -501     |
| Real Det Return     | -107     |
| Real Sto Return     | -163     |
| Running Env Steps   | 4500000  |
| Running Forward KL  | 23.3     |
| Running Reverse KL  | 4.83     |
| Running Update Time | 900      |
----------------------------------
-2024-05-14 07:55:53.062552 ʱ-
| Itration            | 901      |
| Loss                | -475     |
| Real Det Return     | -361     |
| Real Sto Return     | -184     |
| Running Env Steps   | 4505000  |
| Running Forward KL  | 22.3     |
| Running Reverse KL  | 4.2      |
| Running Update Time | 901      |
----------------------------------
-2024-05-14 07:58:22.568182 ʱ-
| Itration            | 902      |
| Loss                | -465     |
| Real Det Return     | -136     |
| Real Sto Return     | -169     |
| Running Env Steps   | 4510000  |
| Running Forward KL  | 21.6     |
| Running Reverse KL  | 4.34     |
| Running Update Time | 902      |
----------------------------------
-2024-05-14 08:00:52.720912 ʱ-
| Itration            | 903      |
| Loss                | -501     |
| Real Det Return     | -326     |
| Real Sto Return     | -167     |
| Running Env Steps   | 4515000  |
| Running Forward KL  | 22.4     |
| Running Reverse KL  | 4.13     |
| Running Update Time | 903      |
----------------------------------
-2024-05-14 08:03:27.075879 ʱ-
| Itration            | 904      |
| Loss                | -488     |
| Real Det Return     | -141     |
| Real Sto Return     | -173     |
| Running Env Steps   | 4520000  |
| Running Forward KL  | 22.6     |
| Running Reverse KL  | 4.11     |
| Running Update Time | 904      |
----------------------------------
-2024-05-14 08:05:56.465546 ʱ-
| Itration            | 905      |
| Loss                | -497     |
| Real Det Return     | -436     |
| Real Sto Return     | -252     |
| Running Env Steps   | 4525000  |
| Running Forward KL  | 23.1     |
| Running Reverse KL  | 4.04     |
| Running Update Time | 905      |
----------------------------------
-2024-05-14 08:08:25.980683 ʱ-
| Itration            | 906      |
| Loss                | -484     |
| Real Det Return     | -132     |
| Real Sto Return     | -204     |
| Running Env Steps   | 4530000  |
| Running Forward KL  | 22.5     |
| Running Reverse KL  | 4.43     |
| Running Update Time | 906      |
----------------------------------
-2024-05-14 08:10:55.624727 ʱ-
| Itration            | 907      |
| Loss                | -518     |
| Real Det Return     | -232     |
| Real Sto Return     | -154     |
| Running Env Steps   | 4535000  |
| Running Forward KL  | 22.5     |
| Running Reverse KL  | 4.02     |
| Running Update Time | 907      |
----------------------------------
-2024-05-14 08:13:25.727053 ʱ-
| Itration            | 908      |
| Loss                | -457     |
| Real Det Return     | -183     |
| Real Sto Return     | -162     |
| Running Env Steps   | 4540000  |
| Running Forward KL  | 22.2     |
| Running Reverse KL  | 4.67     |
| Running Update Time | 908      |
----------------------------------
-2024-05-14 08:15:55.384433 ʱ-
| Itration            | 909      |
| Loss                | -493     |
| Real Det Return     | -183     |
| Real Sto Return     | -211     |
| Running Env Steps   | 4545000  |
| Running Forward KL  | 22.9     |
| Running Reverse KL  | 5.18     |
| Running Update Time | 909      |
----------------------------------
-2024-05-14 08:18:25.508767 ʱ-
| Itration            | 910      |
| Loss                | -461     |
| Real Det Return     | -170     |
| Real Sto Return     | -178     |
| Running Env Steps   | 4550000  |
| Running Forward KL  | 22       |
| Running Reverse KL  | 3.79     |
| Running Update Time | 910      |
----------------------------------
-2024-05-14 08:20:55.334754 ʱ-
| Itration            | 911      |
| Loss                | -460     |
| Real Det Return     | -260     |
| Real Sto Return     | -208     |
| Running Env Steps   | 4555000  |
| Running Forward KL  | 22.4     |
| Running Reverse KL  | 4.83     |
| Running Update Time | 911      |
----------------------------------
-2024-05-14 08:23:25.323326 ʱ-
| Itration            | 912      |
| Loss                | -483     |
| Real Det Return     | -300     |
| Real Sto Return     | -167     |
| Running Env Steps   | 4560000  |
| Running Forward KL  | 22.3     |
| Running Reverse KL  | 4.62     |
| Running Update Time | 912      |
----------------------------------
-2024-05-14 08:25:54.719119 ʱ-
| Itration            | 913      |
| Loss                | -464     |
| Real Det Return     | -109     |
| Real Sto Return     | -166     |
| Running Env Steps   | 4565000  |
| Running Forward KL  | 22.7     |
| Running Reverse KL  | 4.42     |
| Running Update Time | 913      |
----------------------------------
-2024-05-14 08:28:23.969890 ʱ-
| Itration            | 914      |
| Loss                | -514     |
| Real Det Return     | -231     |
| Real Sto Return     | -175     |
| Running Env Steps   | 4570000  |
| Running Forward KL  | 22.8     |
| Running Reverse KL  | 4.4      |
| Running Update Time | 914      |
----------------------------------
-2024-05-14 08:30:54.708838 ʱ-
| Itration            | 915      |
| Loss                | -485     |
| Real Det Return     | -107     |
| Real Sto Return     | -158     |
| Running Env Steps   | 4575000  |
| Running Forward KL  | 22       |
| Running Reverse KL  | 4.21     |
| Running Update Time | 915      |
----------------------------------
-2024-05-14 08:33:24.904759 ʱ-
| Itration            | 916      |
| Loss                | -431     |
| Real Det Return     | -102     |
| Real Sto Return     | -167     |
| Running Env Steps   | 4580000  |
| Running Forward KL  | 21.8     |
| Running Reverse KL  | 4.42     |
| Running Update Time | 916      |
----------------------------------
-2024-05-14 08:35:54.489843 ʱ-
| Itration            | 917      |
| Loss                | -485     |
| Real Det Return     | -148     |
| Real Sto Return     | -181     |
| Running Env Steps   | 4585000  |
| Running Forward KL  | 22.7     |
| Running Reverse KL  | 4.52     |
| Running Update Time | 917      |
----------------------------------
-2024-05-14 08:38:24.206549 ʱ-
| Itration            | 918      |
| Loss                | -476     |
| Real Det Return     | -107     |
| Real Sto Return     | -160     |
| Running Env Steps   | 4590000  |
| Running Forward KL  | 21.9     |
| Running Reverse KL  | 4.06     |
| Running Update Time | 918      |
----------------------------------
-2024-05-14 08:40:53.285149 ʱ-
| Itration            | 919      |
| Loss                | -488     |
| Real Det Return     | -215     |
| Real Sto Return     | -171     |
| Running Env Steps   | 4595000  |
| Running Forward KL  | 23.5     |
| Running Reverse KL  | 5.06     |
| Running Update Time | 919      |
----------------------------------
-2024-05-14 08:43:33.666990 ʱ-
| Itration            | 920      |
| Loss                | -531     |
| Real Det Return     | -105     |
| Real Sto Return     | -168     |
| Running Env Steps   | 4600000  |
| Running Forward KL  | 21.9     |
| Running Reverse KL  | 4.5      |
| Running Update Time | 920      |
----------------------------------
-2024-05-14 08:46:09.092233 ʱ-
| Itration            | 921      |
| Loss                | -492     |
| Real Det Return     | -254     |
| Real Sto Return     | -165     |
| Running Env Steps   | 4605000  |
| Running Forward KL  | 22.4     |
| Running Reverse KL  | 4.12     |
| Running Update Time | 921      |
----------------------------------
-2024-05-14 08:48:47.947770 ʱ-
| Itration            | 922      |
| Loss                | -522     |
| Real Det Return     | -124     |
| Real Sto Return     | -172     |
| Running Env Steps   | 4610000  |
| Running Forward KL  | 22       |
| Running Reverse KL  | 4.25     |
| Running Update Time | 922      |
----------------------------------
-2024-05-14 08:51:17.455884 ʱ-
| Itration            | 923      |
| Loss                | -537     |
| Real Det Return     | -172     |
| Real Sto Return     | -166     |
| Running Env Steps   | 4615000  |
| Running Forward KL  | 22.7     |
| Running Reverse KL  | 4.32     |
| Running Update Time | 923      |
----------------------------------
-2024-05-14 08:53:46.596639 ʱ-
| Itration            | 924      |
| Loss                | -503     |
| Real Det Return     | -233     |
| Real Sto Return     | -188     |
| Running Env Steps   | 4620000  |
| Running Forward KL  | 22.3     |
| Running Reverse KL  | 4.22     |
| Running Update Time | 924      |
----------------------------------
-2024-05-14 08:56:16.614829 ʱ-
| Itration            | 925      |
| Loss                | -512     |
| Real Det Return     | -135     |
| Real Sto Return     | -165     |
| Running Env Steps   | 4625000  |
| Running Forward KL  | 22.7     |
| Running Reverse KL  | 4.98     |
| Running Update Time | 925      |
----------------------------------
-2024-05-14 08:58:46.352140 ʱ-
| Itration            | 926      |
| Loss                | -497     |
| Real Det Return     | -184     |
| Real Sto Return     | -177     |
| Running Env Steps   | 4630000  |
| Running Forward KL  | 22.4     |
| Running Reverse KL  | 4.36     |
| Running Update Time | 926      |
----------------------------------
-2024-05-14 09:01:16.418321 ʱ-
| Itration            | 927      |
| Loss                | -490     |
| Real Det Return     | -289     |
| Real Sto Return     | -169     |
| Running Env Steps   | 4635000  |
| Running Forward KL  | 22.1     |
| Running Reverse KL  | 4.23     |
| Running Update Time | 927      |
----------------------------------
-2024-05-14 09:03:46.340452 ʱ-
| Itration            | 928      |
| Loss                | -498     |
| Real Det Return     | -227     |
| Real Sto Return     | -159     |
| Running Env Steps   | 4640000  |
| Running Forward KL  | 22.6     |
| Running Reverse KL  | 4.46     |
| Running Update Time | 928      |
----------------------------------
-2024-05-14 09:06:16.042575 ʱ-
| Itration            | 929      |
| Loss                | -474     |
| Real Det Return     | -132     |
| Real Sto Return     | -166     |
| Running Env Steps   | 4645000  |
| Running Forward KL  | 22.4     |
| Running Reverse KL  | 4.6      |
| Running Update Time | 929      |
----------------------------------
-2024-05-14 09:08:45.488265 ʱ-
| Itration            | 930      |
| Loss                | -518     |
| Real Det Return     | -325     |
| Real Sto Return     | -199     |
| Running Env Steps   | 4650000  |
| Running Forward KL  | 22.3     |
| Running Reverse KL  | 4.9      |
| Running Update Time | 930      |
----------------------------------
-2024-05-14 09:11:15.927381 ʱ-
| Itration            | 931      |
| Loss                | -501     |
| Real Det Return     | -164     |
| Real Sto Return     | -167     |
| Running Env Steps   | 4655000  |
| Running Forward KL  | 22.6     |
| Running Reverse KL  | 5.11     |
| Running Update Time | 931      |
----------------------------------
-2024-05-14 09:13:45.742374 ʱ-
| Itration            | 932      |
| Loss                | -500     |
| Real Det Return     | -314     |
| Real Sto Return     | -203     |
| Running Env Steps   | 4660000  |
| Running Forward KL  | 22.1     |
| Running Reverse KL  | 4.54     |
| Running Update Time | 932      |
----------------------------------
-2024-05-14 09:16:15.430805 ʱ-
| Itration            | 933      |
| Loss                | -482     |
| Real Det Return     | -200     |
| Real Sto Return     | -157     |
| Running Env Steps   | 4665000  |
| Running Forward KL  | 22.4     |
| Running Reverse KL  | 4.6      |
| Running Update Time | 933      |
----------------------------------
-2024-05-14 09:18:44.947964 ʱ-
| Itration            | 934      |
| Loss                | -514     |
| Real Det Return     | -111     |
| Real Sto Return     | -159     |
| Running Env Steps   | 4670000  |
| Running Forward KL  | 22.2     |
| Running Reverse KL  | 4.81     |
| Running Update Time | 934      |
----------------------------------
-2024-05-14 09:21:14.978710 ʱ-
| Itration            | 935      |
| Loss                | -491     |
| Real Det Return     | -220     |
| Real Sto Return     | -178     |
| Running Env Steps   | 4675000  |
| Running Forward KL  | 22       |
| Running Reverse KL  | 4.15     |
| Running Update Time | 935      |
----------------------------------
-2024-05-14 09:23:44.094903 ʱ-
| Itration            | 936      |
| Loss                | -504     |
| Real Det Return     | -240     |
| Real Sto Return     | -170     |
| Running Env Steps   | 4680000  |
| Running Forward KL  | 22.4     |
| Running Reverse KL  | 4.18     |
| Running Update Time | 936      |
----------------------------------
-2024-05-14 09:26:13.516041 ʱ-
| Itration            | 937      |
| Loss                | -505     |
| Real Det Return     | -204     |
| Real Sto Return     | -166     |
| Running Env Steps   | 4685000  |
| Running Forward KL  | 22       |
| Running Reverse KL  | 4.6      |
| Running Update Time | 937      |
----------------------------------
-2024-05-14 09:28:43.490174 ʱ-
| Itration            | 938      |
| Loss                | -506     |
| Real Det Return     | -160     |
| Real Sto Return     | -187     |
| Running Env Steps   | 4690000  |
| Running Forward KL  | 22.4     |
| Running Reverse KL  | 4.17     |
| Running Update Time | 938      |
----------------------------------
-2024-05-14 09:31:13.681980 ʱ-
| Itration            | 939      |
| Loss                | -483     |
| Real Det Return     | -214     |
| Real Sto Return     | -164     |
| Running Env Steps   | 4695000  |
| Running Forward KL  | 22       |
| Running Reverse KL  | 4.31     |
| Running Update Time | 939      |
----------------------------------
-2024-05-14 09:33:43.203007 ʱ-
| Itration            | 940      |
| Loss                | -508     |
| Real Det Return     | -245     |
| Real Sto Return     | -167     |
| Running Env Steps   | 4700000  |
| Running Forward KL  | 21.9     |
| Running Reverse KL  | 3.99     |
| Running Update Time | 940      |
----------------------------------
-2024-05-14 09:36:13.724045 ʱ-
| Itration            | 941      |
| Loss                | -488     |
| Real Det Return     | -87.8    |
| Real Sto Return     | -161     |
| Running Env Steps   | 4705000  |
| Running Forward KL  | 22.5     |
| Running Reverse KL  | 4.52     |
| Running Update Time | 941      |
----------------------------------
-2024-05-14 09:38:43.168399 ʱ-
| Itration            | 942      |
| Loss                | -494     |
| Real Det Return     | -135     |
| Real Sto Return     | -163     |
| Running Env Steps   | 4710000  |
| Running Forward KL  | 22.4     |
| Running Reverse KL  | 4.85     |
| Running Update Time | 942      |
----------------------------------
-2024-05-14 09:41:12.044260 ʱ-
| Itration            | 943      |
| Loss                | -489     |
| Real Det Return     | -128     |
| Real Sto Return     | -166     |
| Running Env Steps   | 4715000  |
| Running Forward KL  | 21.8     |
| Running Reverse KL  | 3.93     |
| Running Update Time | 943      |
----------------------------------
-2024-05-14 09:43:42.081157 ʱ-
| Itration            | 944      |
| Loss                | -486     |
| Real Det Return     | -174     |
| Real Sto Return     | -169     |
| Running Env Steps   | 4720000  |
| Running Forward KL  | 21.7     |
| Running Reverse KL  | 4.37     |
| Running Update Time | 944      |
----------------------------------
-2024-05-14 09:46:11.221297 ʱ-
| Itration            | 945      |
| Loss                | -540     |
| Real Det Return     | -235     |
| Real Sto Return     | -156     |
| Running Env Steps   | 4725000  |
| Running Forward KL  | 21.2     |
| Running Reverse KL  | 3.71     |
| Running Update Time | 945      |
----------------------------------
-2024-05-14 09:48:41.584522 ʱ-
| Itration            | 946      |
| Loss                | -528     |
| Real Det Return     | -229     |
| Real Sto Return     | -187     |
| Running Env Steps   | 4730000  |
| Running Forward KL  | 22.7     |
| Running Reverse KL  | 3.83     |
| Running Update Time | 946      |
----------------------------------
-2024-05-14 09:51:11.119161 ʱ-
| Itration            | 947      |
| Loss                | -483     |
| Real Det Return     | -222     |
| Real Sto Return     | -171     |
| Running Env Steps   | 4735000  |
| Running Forward KL  | 22.1     |
| Running Reverse KL  | 4.17     |
| Running Update Time | 947      |
----------------------------------
-2024-05-14 09:53:40.809322 ʱ-
| Itration            | 948      |
| Loss                | -523     |
| Real Det Return     | -135     |
| Real Sto Return     | -160     |
| Running Env Steps   | 4740000  |
| Running Forward KL  | 21.5     |
| Running Reverse KL  | 3.97     |
| Running Update Time | 948      |
----------------------------------
-2024-05-14 09:56:11.139799 ʱ-
| Itration            | 949      |
| Loss                | -482     |
| Real Det Return     | -90.8    |
| Real Sto Return     | -163     |
| Running Env Steps   | 4745000  |
| Running Forward KL  | 21.3     |
| Running Reverse KL  | 3.88     |
| Running Update Time | 949      |
----------------------------------
-2024-05-14 09:58:40.816157 ʱ-
| Itration            | 950      |
| Loss                | -513     |
| Real Det Return     | -113     |
| Real Sto Return     | -156     |
| Running Env Steps   | 4750000  |
| Running Forward KL  | 21.4     |
| Running Reverse KL  | 4.42     |
| Running Update Time | 950      |
----------------------------------
-2024-05-14 10:01:10.343498 ʱ-
| Itration            | 951      |
| Loss                | -496     |
| Real Det Return     | -135     |
| Real Sto Return     | -164     |
| Running Env Steps   | 4755000  |
| Running Forward KL  | 22.2     |
| Running Reverse KL  | 4.63     |
| Running Update Time | 951      |
----------------------------------
-2024-05-14 10:03:40.448836 ʱ-
| Itration            | 952      |
| Loss                | -538     |
| Real Det Return     | -204     |
| Real Sto Return     | -167     |
| Running Env Steps   | 4760000  |
| Running Forward KL  | 21.9     |
| Running Reverse KL  | 4.21     |
| Running Update Time | 952      |
----------------------------------
-2024-05-14 10:06:10.591501 ʱ-
| Itration            | 953      |
| Loss                | -526     |
| Real Det Return     | -145     |
| Real Sto Return     | -153     |
| Running Env Steps   | 4765000  |
| Running Forward KL  | 21.4     |
| Running Reverse KL  | 4.05     |
| Running Update Time | 953      |
----------------------------------
-2024-05-14 10:08:40.423272 ʱ-
| Itration            | 954      |
| Loss                | -514     |
| Real Det Return     | -105     |
| Real Sto Return     | -169     |
| Running Env Steps   | 4770000  |
| Running Forward KL  | 21.5     |
| Running Reverse KL  | 4.63     |
| Running Update Time | 954      |
----------------------------------
-2024-05-14 10:11:10.661584 ʱ-
| Itration            | 955      |
| Loss                | -543     |
| Real Det Return     | -248     |
| Real Sto Return     | -182     |
| Running Env Steps   | 4775000  |
| Running Forward KL  | 22.2     |
| Running Reverse KL  | 4.15     |
| Running Update Time | 955      |
----------------------------------
-2024-05-14 10:13:40.056955 ʱ-
| Itration            | 956      |
| Loss                | -515     |
| Real Det Return     | -196     |
| Real Sto Return     | -161     |
| Running Env Steps   | 4780000  |
| Running Forward KL  | 21.9     |
| Running Reverse KL  | 4.79     |
| Running Update Time | 956      |
----------------------------------
-2024-05-14 10:16:09.885781 ʱ-
| Itration            | 957      |
| Loss                | -519     |
| Real Det Return     | -90.8    |
| Real Sto Return     | -167     |
| Running Env Steps   | 4785000  |
| Running Forward KL  | 22.2     |
| Running Reverse KL  | 4.58     |
| Running Update Time | 957      |
----------------------------------
-2024-05-14 10:18:39.870445 ʱ-
| Itration            | 958      |
| Loss                | -498     |
| Real Det Return     | -92.4    |
| Real Sto Return     | -154     |
| Running Env Steps   | 4790000  |
| Running Forward KL  | 22       |
| Running Reverse KL  | 4.62     |
| Running Update Time | 958      |
----------------------------------
-2024-05-14 10:21:09.798558 ʱ-
| Itration            | 959      |
| Loss                | -515     |
| Real Det Return     | -216     |
| Real Sto Return     | -170     |
| Running Env Steps   | 4795000  |
| Running Forward KL  | 21.6     |
| Running Reverse KL  | 4.14     |
| Running Update Time | 959      |
----------------------------------
-2024-05-14 10:23:40.035197 ʱ-
| Itration            | 960      |
| Loss                | -524     |
| Real Det Return     | -263     |
| Real Sto Return     | -184     |
| Running Env Steps   | 4800000  |
| Running Forward KL  | 23.1     |
| Running Reverse KL  | 5.09     |
| Running Update Time | 960      |
----------------------------------
-2024-05-14 10:26:09.569803 ʱ-
| Itration            | 961      |
| Loss                | -517     |
| Real Det Return     | -86.5    |
| Real Sto Return     | -180     |
| Running Env Steps   | 4805000  |
| Running Forward KL  | 21.8     |
| Running Reverse KL  | 4.77     |
| Running Update Time | 961      |
----------------------------------
-2024-05-14 10:28:39.776431 ʱ-
| Itration            | 962      |
| Loss                | -545     |
| Real Det Return     | -98.7    |
| Real Sto Return     | -156     |
| Running Env Steps   | 4810000  |
| Running Forward KL  | 22.1     |
| Running Reverse KL  | 4.33     |
| Running Update Time | 962      |
----------------------------------
-2024-05-14 10:31:11.985858 ʱ-
| Itration            | 963      |
| Loss                | -537     |
| Real Det Return     | -326     |
| Real Sto Return     | -203     |
| Running Env Steps   | 4815000  |
| Running Forward KL  | 21.9     |
| Running Reverse KL  | 4.2      |
| Running Update Time | 963      |
----------------------------------
-2024-05-14 10:33:41.899653 ʱ-
| Itration            | 964      |
| Loss                | -500     |
| Real Det Return     | -166     |
| Real Sto Return     | -157     |
| Running Env Steps   | 4820000  |
| Running Forward KL  | 21.5     |
| Running Reverse KL  | 4.43     |
| Running Update Time | 964      |
----------------------------------
-2024-05-14 10:36:11.986159 ʱ-
| Itration            | 965      |
| Loss                | -571     |
| Real Det Return     | -303     |
| Real Sto Return     | -197     |
| Running Env Steps   | 4825000  |
| Running Forward KL  | 21.7     |
| Running Reverse KL  | 3.8      |
| Running Update Time | 965      |
----------------------------------
-2024-05-14 10:38:42.191282 ʱ-
| Itration            | 966      |
| Loss                | -520     |
| Real Det Return     | -173     |
| Real Sto Return     | -185     |
| Running Env Steps   | 4830000  |
| Running Forward KL  | 21.8     |
| Running Reverse KL  | 4.17     |
| Running Update Time | 966      |
----------------------------------
-2024-05-14 10:41:11.959221 ʱ-
| Itration            | 967      |
| Loss                | -584     |
| Real Det Return     | -200     |
| Real Sto Return     | -180     |
| Running Env Steps   | 4835000  |
| Running Forward KL  | 21.5     |
| Running Reverse KL  | 3.87     |
| Running Update Time | 967      |
----------------------------------
-2024-05-14 10:43:41.944366 ʱ-
| Itration            | 968      |
| Loss                | -533     |
| Real Det Return     | -127     |
| Real Sto Return     | -138     |
| Running Env Steps   | 4840000  |
| Running Forward KL  | 21.9     |
| Running Reverse KL  | 4.47     |
| Running Update Time | 968      |
----------------------------------
-2024-05-14 10:46:11.260596 ʱ-
| Itration            | 969      |
| Loss                | -521     |
| Real Det Return     | -135     |
| Real Sto Return     | -167     |
| Running Env Steps   | 4845000  |
| Running Forward KL  | 21.4     |
| Running Reverse KL  | 4.03     |
| Running Update Time | 969      |
----------------------------------
-2024-05-14 10:48:41.291610 ʱ-
| Itration            | 970      |
| Loss                | -571     |
| Real Det Return     | -115     |
| Real Sto Return     | -147     |
| Running Env Steps   | 4850000  |
| Running Forward KL  | 21.8     |
| Running Reverse KL  | 4.35     |
| Running Update Time | 970      |
----------------------------------
-2024-05-14 10:51:11.417875 ʱ-
| Itration            | 971      |
| Loss                | -529     |
| Real Det Return     | -154     |
| Real Sto Return     | -146     |
| Running Env Steps   | 4855000  |
| Running Forward KL  | 22.1     |
| Running Reverse KL  | 4.92     |
| Running Update Time | 971      |
----------------------------------
-2024-05-14 10:53:43.184991 ʱ-
| Itration            | 972      |
| Loss                | -562     |
| Real Det Return     | -181     |
| Real Sto Return     | -186     |
| Running Env Steps   | 4860000  |
| Running Forward KL  | 22.5     |
| Running Reverse KL  | 5.03     |
| Running Update Time | 972      |
----------------------------------
-2024-05-14 10:56:14.170075 ʱ-
| Itration            | 973      |
| Loss                | -501     |
| Real Det Return     | -98.7    |
| Real Sto Return     | -146     |
| Running Env Steps   | 4865000  |
| Running Forward KL  | 21.9     |
| Running Reverse KL  | 4.87     |
| Running Update Time | 973      |
----------------------------------
-2024-05-14 10:58:44.670638 ʱ-
| Itration            | 974      |
| Loss                | -569     |
| Real Det Return     | -238     |
| Real Sto Return     | -165     |
| Running Env Steps   | 4870000  |
| Running Forward KL  | 21.7     |
| Running Reverse KL  | 4.29     |
| Running Update Time | 974      |
----------------------------------
-2024-05-14 11:01:14.734958 ʱ-
| Itration            | 975      |
| Loss                | -507     |
| Real Det Return     | -93.8    |
| Real Sto Return     | -143     |
| Running Env Steps   | 4875000  |
| Running Forward KL  | 21.8     |
| Running Reverse KL  | 4.12     |
| Running Update Time | 975      |
----------------------------------
-2024-05-14 11:03:44.796044 ʱ-
| Itration            | 976      |
| Loss                | -567     |
| Real Det Return     | -160     |
| Real Sto Return     | -155     |
| Running Env Steps   | 4880000  |
| Running Forward KL  | 21       |
| Running Reverse KL  | 3.82     |
| Running Update Time | 976      |
----------------------------------
-2024-05-14 11:06:15.159943 ʱ-
| Itration            | 977      |
| Loss                | -515     |
| Real Det Return     | -119     |
| Real Sto Return     | -167     |
| Running Env Steps   | 4885000  |
| Running Forward KL  | 21.2     |
| Running Reverse KL  | 4.73     |
| Running Update Time | 977      |
----------------------------------
-2024-05-14 11:08:47.422530 ʱ-
| Itration            | 978      |
| Loss                | -527     |
| Real Det Return     | -87.8    |
| Real Sto Return     | -167     |
| Running Env Steps   | 4890000  |
| Running Forward KL  | 22       |
| Running Reverse KL  | 4.56     |
| Running Update Time | 978      |
----------------------------------
-2024-05-14 11:11:19.128375 ʱ-
| Itration            | 979      |
| Loss                | -527     |
| Real Det Return     | -140     |
| Real Sto Return     | -137     |
| Running Env Steps   | 4895000  |
| Running Forward KL  | 21.4     |
| Running Reverse KL  | 4.23     |
| Running Update Time | 979      |
----------------------------------
-2024-05-14 11:13:51.448244 ʱ-
| Itration            | 980      |
| Loss                | -529     |
| Real Det Return     | -151     |
| Real Sto Return     | -148     |
| Running Env Steps   | 4900000  |
| Running Forward KL  | 21.8     |
| Running Reverse KL  | 4.71     |
| Running Update Time | 980      |
----------------------------------
-2024-05-14 11:16:22.960609 ʱ-
| Itration            | 981      |
| Loss                | -528     |
| Real Det Return     | -93.4    |
| Real Sto Return     | -166     |
| Running Env Steps   | 4905000  |
| Running Forward KL  | 21.3     |
| Running Reverse KL  | 4.21     |
| Running Update Time | 981      |
----------------------------------
-2024-05-14 11:18:55.224408 ʱ-
| Itration            | 982      |
| Loss                | -567     |
| Real Det Return     | -290     |
| Real Sto Return     | -177     |
| Running Env Steps   | 4910000  |
| Running Forward KL  | 21.5     |
| Running Reverse KL  | 3.88     |
| Running Update Time | 982      |
----------------------------------
-2024-05-14 11:21:27.688369 ʱ-
| Itration            | 983      |
| Loss                | -577     |
| Real Det Return     | -183     |
| Real Sto Return     | -144     |
| Running Env Steps   | 4915000  |
| Running Forward KL  | 21.5     |
| Running Reverse KL  | 3.88     |
| Running Update Time | 983      |
----------------------------------
-2024-05-14 11:23:59.657531 ʱ-
| Itration            | 984      |
| Loss                | -564     |
| Real Det Return     | -247     |
| Real Sto Return     | -168     |
| Running Env Steps   | 4920000  |
| Running Forward KL  | 21.3     |
| Running Reverse KL  | 3.87     |
| Running Update Time | 984      |
----------------------------------
-2024-05-14 11:26:31.215962 ʱ-
| Itration            | 985      |
| Loss                | -579     |
| Real Det Return     | -205     |
| Real Sto Return     | -160     |
| Running Env Steps   | 4925000  |
| Running Forward KL  | 22.3     |
| Running Reverse KL  | 5.02     |
| Running Update Time | 985      |
----------------------------------
-2024-05-14 11:29:04.093835 ʱ-
| Itration            | 986      |
| Loss                | -573     |
| Real Det Return     | -141     |
| Real Sto Return     | -160     |
| Running Env Steps   | 4930000  |
| Running Forward KL  | 21.6     |
| Running Reverse KL  | 4.61     |
| Running Update Time | 986      |
----------------------------------
-2024-05-14 11:31:35.818832 ʱ-
| Itration            | 987      |
| Loss                | -529     |
| Real Det Return     | -295     |
| Real Sto Return     | -216     |
| Running Env Steps   | 4935000  |
| Running Forward KL  | 21       |
| Running Reverse KL  | 3.67     |
| Running Update Time | 987      |
----------------------------------
-2024-05-14 11:34:07.478383 ʱ-
| Itration            | 988      |
| Loss                | -535     |
| Real Det Return     | -142     |
| Real Sto Return     | -162     |
| Running Env Steps   | 4940000  |
| Running Forward KL  | 21.7     |
| Running Reverse KL  | 4.71     |
| Running Update Time | 988      |
----------------------------------
-2024-05-14 11:36:39.441977 ʱ-
| Itration            | 989      |
| Loss                | -545     |
| Real Det Return     | -297     |
| Real Sto Return     | -199     |
| Running Env Steps   | 4945000  |
| Running Forward KL  | 21.9     |
| Running Reverse KL  | 4.43     |
| Running Update Time | 989      |
----------------------------------
-2024-05-14 11:39:11.364851 ʱ-
| Itration            | 990      |
| Loss                | -508     |
| Real Det Return     | -107     |
| Real Sto Return     | -155     |
| Running Env Steps   | 4950000  |
| Running Forward KL  | 21.4     |
| Running Reverse KL  | 4.78     |
| Running Update Time | 990      |
----------------------------------
-2024-05-14 11:41:42.900230 ʱ-
| Itration            | 991      |
| Loss                | -539     |
| Real Det Return     | -93.5    |
| Real Sto Return     | -173     |
| Running Env Steps   | 4955000  |
| Running Forward KL  | 21.5     |
| Running Reverse KL  | 4.87     |
| Running Update Time | 991      |
----------------------------------
-2024-05-14 11:44:15.728926 ʱ-
| Itration            | 992      |
| Loss                | -523     |
| Real Det Return     | -90.6    |
| Real Sto Return     | -145     |
| Running Env Steps   | 4960000  |
| Running Forward KL  | 21       |
| Running Reverse KL  | 4.42     |
| Running Update Time | 992      |
----------------------------------
-2024-05-14 11:46:47.653277 ʱ-
| Itration            | 993      |
| Loss                | -543     |
| Real Det Return     | -104     |
| Real Sto Return     | -213     |
| Running Env Steps   | 4965000  |
| Running Forward KL  | 21.9     |
| Running Reverse KL  | 5.37     |
| Running Update Time | 993      |
----------------------------------
-2024-05-14 11:49:20.145199 ʱ-
| Itration            | 994      |
| Loss                | -561     |
| Real Det Return     | -113     |
| Real Sto Return     | -173     |
| Running Env Steps   | 4970000  |
| Running Forward KL  | 21.5     |
| Running Reverse KL  | 4.74     |
| Running Update Time | 994      |
----------------------------------
-2024-05-14 11:51:52.068789 ʱ-
| Itration            | 995      |
| Loss                | -560     |
| Real Det Return     | -79.9    |
| Real Sto Return     | -168     |
| Running Env Steps   | 4975000  |
| Running Forward KL  | 22.2     |
| Running Reverse KL  | 5.25     |
| Running Update Time | 995      |
----------------------------------
-2024-05-14 11:54:24.282467 ʱ-
| Itration            | 996      |
| Loss                | -546     |
| Real Det Return     | -396     |
| Real Sto Return     | -218     |
| Running Env Steps   | 4980000  |
| Running Forward KL  | 21.6     |
| Running Reverse KL  | 4.33     |
| Running Update Time | 996      |
----------------------------------
-2024-05-14 11:56:56.199463 ʱ-
| Itration            | 997      |
| Loss                | -538     |
| Real Det Return     | -252     |
| Real Sto Return     | -147     |
| Running Env Steps   | 4985000  |
| Running Forward KL  | 20.8     |
| Running Reverse KL  | 3.87     |
| Running Update Time | 997      |
----------------------------------
-2024-05-14 11:59:28.769094 ʱ-
| Itration            | 998      |
| Loss                | -535     |
| Real Det Return     | -214     |
| Real Sto Return     | -177     |
| Running Env Steps   | 4990000  |
| Running Forward KL  | 21.7     |
| Running Reverse KL  | 4.55     |
| Running Update Time | 998      |
----------------------------------
-2024-05-14 12:02:01.037900 ʱ-
| Itration            | 999      |
| Loss                | -577     |
| Real Det Return     | -260     |
| Real Sto Return     | -186     |
| Running Env Steps   | 4995000  |
| Running Forward KL  | 21.2     |
| Running Reverse KL  | 4.48     |
| Running Update Time | 999      |
----------------------------------
