@inproceedings{NIPS2017_a1d7311f, author = {Gu, Shixiang (Shane) and Lillicrap, Timothy and Turner, Richard E and Ghahramani, Zoubin and Sch\"{o}lkopf, Bernhard and Levine, Sergey}, booktitle = {Advances in Neural Information Processing Systems}, editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett}, pages = {}, publisher = {Curran Associates, Inc.}, title = {Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning}, url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/a1d7311f2a312426d710e1c617fcbc8c-Paper.pdf}, volume = {30}, year = {2017} }