时序差分方法

1. Motivating examples

2. TD learning of state values

3. TD learning of action values: Sarsa

4. TD learning of action values: Expected Sarsa

5. TD learning of action values: n-step Sarsa

6. TD learning of optimal action values: Q-learning

7. A unified point of view

8. Summary

参考文献

本文是一篇学习笔记，内容全部源自于以下视频

https://www.bilibili.com/video/BV1Pz5C6iE3X/?p=6&spm_id_from=333.1007.top_right_bar_window_history.content.click&vd_source=44ed90827c8f67247cab0ab288133c80