Supplementary materials for paper titled
"Log-normality and Skewness of Estimated State/Action Values in Reinforcement Learning"
by Liangpeng Zhang (lxz472@cs.bham.ac.uk)

Including files:

\chain\data\*.txt
	all experimental results on chain MDPs presented in Section 5

\chain\source code\test.lua
	testing environment and value iteration algorithm, written in lua.

\chain\source code\seeDistribution.m
	matlab script for drawing Figure 5 (a)

\chain\source code\checkData.m
	matlab script for drawing Figure 5 (b)

\chain\source code\EstimateMeanStdQ.m
	matlab implementation of Lemma 3.5 & 3.6.

\maze\testGenMaze.lua
	test scripts for maze experiments, written in lua.

\maze\logsMaze\*.txt
	all experimental results on mazes presented in Section 5

\two skewed\drawTwoSkewedFigure1New.m
	matlab script for drawing Figure 1 and compute Pr(X2>X1).

