readme.txt

来自「approximate reinforcement learning」· 文本 代码 · 共 8 行

/int_mdp, /int_problem
	Problem and MDP definition of a simple discrete-time integrator
	 for approximate RL
/int_optimal
	RL solution: optimal Q-function and policy
/int_plotoptimal
	Script to plot a nice picture of the Q-function and lay policy on
	top of it.