文章目录

time difference learningSARSA Monte Carlo Methods两种算法的对比 参考书籍： reinforcement learning : state-of-the-art an introduction to reinforcement(Sutton) 上一篇笔记： https://blog.csdn.net/Jinyindao243052/article/details/106985000

time difference learning

SARSA

Monte Carlo Methods

V函数的 Monte Carlo learning Monte Carlo 方法估计 $V(S)$ Monte Carlo 方法更新最优策略 算法1 算法2

两种算法的对比