强化学习目录

论文笔记

1. [Nature 2016] AlphaGo: Deep RL 与 Tree Search 的成功结合
2. [Nature 2018] AlphaGo Zero: 无需监督学习的AlphaGo
3. [Nature 2015] DQN论文笔记 及 实现
4. [ICML 2016] A3C
5. [ICLR 2016] Prioritized Experience Replay
6. [AAAI 2016] Double DQN
7. [ICML 2016] Dueling DQN
8. [ICML 2017] Distributional RL
9. [AAAI 2018] Rainbow

代码实现

1. [python] 在 tic-tac-toe 上实现 蒙特卡洛搜索树 MCTS 算法

RL: An Introduction, second edition, by Sutton and Barto 读书笔记