diff --git a/README.md b/README.md index 65b90c0..b5c9289 100644 --- a/README.md +++ b/README.md @@ -30,23 +30,23 @@ | [第十三章 AlphaStar 论文解读](https://datawhalechina.github.io/easy-rl/#/chapter13/chapter13) | | | ## 算法实战 -| 算法名称 | 相关论文材料 | 备注 | 环境 | -| :----------------------------------------------------------: | :---------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | -| [On-Policy First-Visit MC](https://github.com/datawhalechina/easy-rl/tree/master/codes/MonteCarlo) | | 蒙特卡洛算法 | [Racetrack](https://github.com/datawhalechina/easy-rl/blob/master/codes/envs/racetrack_env.md) | -| [Q-Learning](https://github.com/datawhalechina/easy-rl/tree/master/codes/QLearning) | | | [CliffWalking-v0](https://github.com/datawhalechina/easy-rl/blob/master/codes/envs/gym_info.md) | -| [Sarsa](https://github.com/datawhalechina/easy-rl/tree/master/codes/Sarsa) | | | [Racetrack](https://github.com/datawhalechina/easy-rl/blob/master/codes/envs/racetrack_env.md) | -| [DQN](https://github.com/datawhalechina/easy-rl/tree/master/codes/DQN) | [DQN-paper](https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf) | [DQN算法实战](https://blog.csdn.net/JohnJim0/article/details/109557173) | [CartPole-v0](https://github.com/datawhalechina/easy-rl/blob/master/codes/envs/gym_info.md) | -| DQN-cnn | [DQN-paper](https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf) | 与DQN相比使用了CNN而不是全链接网络 | [CartPole-v0](https://github.com/datawhalechina/easy-rl/blob/master/codes/envs/gym_info.md) | -| [DoubleDQN](https://github.com/datawhalechina/easy-rl/tree/master/codes/DoubleDQN) | | | [CartPole-v0](https://github.com/datawhalechina/easy-rl/blob/master/codes/envs/gym_info.md) | -| Hierarchical DQN | [Hierarchical DQN](https://arxiv.org/abs/1604.06057) | | | -| [PolicyGradient](https://github.com/datawhalechina/easy-rl/tree/master/codes/PolicyGradient) | | | [CartPole-v0](https://github.com/datawhalechina/easy-rl/blob/master/codes/envs/gym_info.md) | -| [A2C](https://github.com/datawhalechina/easy-rl/tree/master/codes/A2C) | | | [CartPole-v0](https://github.com/datawhalechina/easy-rl/blob/master/codes/envs/gym_info.md) | -| A3C | | | | -| SAC | | | | -| [PPO](https://github.com/datawhalechina/easy-rl/tree/master/codes/PPO) | [PPO paper](https://arxiv.org/abs/1707.06347) | [PPO算法实战](https://blog.csdn.net/JohnJim0/article/details/115126363) | [CartPole-v0](https://github.com/datawhalechina/easy-rl/blob/master/codes/envs/gym_info.md) | -| DDPG | [DDPG Paper](https://arxiv.org/abs/1509.02971) | | [Pendulum-v0](https://github.com/datawhalechina/easy-rl/blob/master/codes/envs/gym_info.md) | -| TD3 | [Twin Dueling DDPG Paper](https://arxiv.org/abs/1802.09477) | | | -| GAIL | | | | +| 算法名称 | 相关论文材料 | 环境 | 备注 | +| :--------------------------------------: | :---------------------------------------------------------: | ------------------------------------- | :--------------------------------: | +| [On-Policy First-Visit MC](./codes/MonteCarlo) | | [Racetrack](./codes/envs/racetrack_env.md) | | +| [Q-Learning](./codes/QLearning) | | [CliffWalking-v0](./codes/envs/gym_info.md) | | +| [Sarsa](./codes/Sarsa) | | [Racetrack](./codes/envs/racetrack_env.md) | | +| [DQN](./codes/DQN) | [DQN-paper](https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf) | [CartPole-v0](./codes/envs/gym_info.md) | | +| DQN-cnn | [DQN-paper](https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf) | [CartPole-v0](./codes/envs/gym_info.md) | 与DQN相比使用了CNN而不是全链接网络 | +| [DoubleDQN](./codes/DoubleDQN) | | [CartPole-v0](./codes/envs/gym_info.md) | 效果不好，待改进 | +| Hierarchical DQN | [Hierarchical DQN](https://arxiv.org/abs/1604.06057) | | | +| [PolicyGradient](./codes/PolicyGradient) | | [CartPole-v0](./codes/envs/gym_info.md) | | +| A2C | | [CartPole-v0](./codes/envs/gym_info.md) | | +| A3C | | | | +| SAC | | | | +| [PPO](./codes/PPO) | [PPO paper](https://arxiv.org/abs/1707.06347) | [CartPole-v0](./codes/envs/gym_info.md) | | +| DDPG | [DDPG Paper](https://arxiv.org/abs/1509.02971) | [Pendulum-v0](./codes/envs/gym_info.md) | | +| TD3 | [Twin Dueling DDPG Paper](https://arxiv.org/abs/1802.09477) | | | +| GAIL | | | | ## 贡献者 diff --git a/docs/README.md b/docs/README.md index 99328a2..b4a4ce9 100644 --- a/docs/README.md +++ b/docs/README.md @@ -13,37 +13,40 @@ 地址：https://datawhalechina.github.io/easy-rl/ ## 内容导航 -| 章节 | 习题 | 项目 | +| 章节 | 习题 | 相关项目 | | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | | [第一章 强化学习概述](https://datawhalechina.github.io/easy-rl/#/chapter1/chapter1) | [第一章 习题](https://datawhalechina.github.io/easy-rl/#/chapter1/chapter1_questions&keywords) | | | [第二章 马尔可夫决策过程 (MDP)](https://datawhalechina.github.io/easy-rl/#/chapter2/chapter2) | [第二章 习题](https://datawhalechina.github.io/easy-rl/#/chapter2/chapter2_questions&keywords) | | -| [第三章 表格型方法](https://datawhalechina.github.io/easy-rl/#/chapter3/chapter3) | [第三章 习题](https://datawhalechina.github.io/easy-rl/#/chapter3/chapter3_questions&keywords) | [项目一 使用 Q-learning 解决悬崖寻路问题](https://datawhalechina.github.io/easy-rl/#/chapter3/project1) | +| [第三章 表格型方法](https://datawhalechina.github.io/easy-rl/#/chapter3/chapter3) | [第三章 习题](https://datawhalechina.github.io/easy-rl/#/chapter3/chapter3_questions&keywords) | [Q-learning算法实战](https://datawhalechina.github.io/easy-rl/#/chapter3/project1) | | [第四章 策略梯度](https://datawhalechina.github.io/easy-rl/#/chapter4/chapter4) | [第四章 习题](https://datawhalechina.github.io/easy-rl/#/chapter4/chapter4_questions&keywords) | | | [第五章 近端策略优化 (PPO) 算法](https://datawhalechina.github.io/easy-rl/#/chapter5/chapter5) | [第五章 习题](https://datawhalechina.github.io/easy-rl/#/chapter5/chapter5_questions&keywords) | | | [第六章 DQN (基本概念)](https://datawhalechina.github.io/easy-rl/#/chapter6/chapter6) | [第六章 习题](https://datawhalechina.github.io/easy-rl/#/chapter6/chapter6_questions&keywords) | | -| [第七章 DQN (进阶技巧)](https://datawhalechina.github.io/easy-rl/#/chapter7/chapter7) | [第七章 习题](https://datawhalechina.github.io/easy-rl/#/chapter7/chapter7_questions&keywords) | [项目二 使用 DQN 实现 CartPole-v0](https://datawhalechina.github.io/easy-rl/#/chapter7/project2) | +| [第七章 DQN (进阶技巧)](https://datawhalechina.github.io/easy-rl/#/chapter7/chapter7) | [第七章 习题](https://datawhalechina.github.io/easy-rl/#/chapter7/chapter7_questions&keywords) | [DQN算法实战](https://datawhalechina.github.io/easy-rl/#/chapter7/project2) | | [第八章 DQN (连续动作)](https://datawhalechina.github.io/easy-rl/#/chapter8/chapter8) | [第八章 习题](https://datawhalechina.github.io/easy-rl/#/chapter8/chapter8_questions&keywords) | | | [第九章 演员-评论家算法](https://datawhalechina.github.io/easy-rl/#/chapter9/chapter9) | [第九章 习题](https://datawhalechina.github.io/easy-rl/#/chapter9/chapter9_questions&keywords) | | | [第十章 稀疏奖励](https://datawhalechina.github.io/easy-rl/#/chapter10/chapter10) | [第十章 习题](https://datawhalechina.github.io/easy-rl/#/chapter10/chapter10_questions&keywords) | | | [第十一章 模仿学习](https://datawhalechina.github.io/easy-rl/#/chapter11/chapter11) | [第十一章 习题](https://datawhalechina.github.io/easy-rl/#/chapter11/chapter11_questions&keywords) | | -| [第十二章 深度确定性策略梯度 (DDPG) 算法](https://datawhalechina.github.io/easy-rl/#/chapter12/chapter12) | [第十二章 习题](https://datawhalechina.github.io/easy-rl/#/chapter12/chapter12_questions&keywords) | [项目三 使用 Policy-Based 方法实现 Pendulum-v0](https://datawhalechina.github.io/easy-rl/#/chapter12/project3) | -| [第十三章 AlphaStar 论文解读](https://datawhalechina.github.io/easy-rl/#/chapter13/chapter13) ||| -## 算法代码实现一览 +| [第十二章 深度确定性策略梯度 (DDPG) 算法](https://datawhalechina.github.io/easy-rl/#/chapter12/chapter12) | [第十二章 习题](https://datawhalechina.github.io/easy-rl/#/chapter12/chapter12_questions&keywords) | [DDPG算法实战](https://datawhalechina.github.io/easy-rl/#/chapter12/project3) | +| [第十三章 AlphaStar 论文解读](https://datawhalechina.github.io/easy-rl/#/chapter13/chapter13) | | | +## 算法实战 -| 算法名称 | 相关论文材料 | 备注 | 进度 | -| :----------------------------------------------------------: | :---------------------------------------------------------: | :----------------------------------------------------------: | :--: | -| [On-Policy First-Visit MC](https://github.com/datawhalechina/easy-rl/tree/master/codes/MonteCarlo) | | 蒙特卡洛算法 | OK | -| [Q-Learning](https://github.com/datawhalechina/easy-rl/tree/master/codes/QLearning) | | | OK | -| [Sarsa](https://github.com/datawhalechina/easy-rl/tree/master/codes/Sarsa) | | | OK | -| [DQN](https://github.com/datawhalechina/easy-rl/tree/master/codes/DQN) | [DQN-paper](https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf) | | OK | -| DQN-cnn | [DQN-paper](https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf) | 与DQN相比使用了CNN而不是全链接网络 | OK | -| [DoubleDQN](https://github.com/datawhalechina/easy-rl/tree/master/codes/DoubleDQN) | | | OK | -| Hierarchical DQN | [Hierarchical DQN](https://arxiv.org/abs/1604.06057) | | | -| [PolicyGradient](https://github.com/datawhalechina/easy-rl/tree/master/codes/PolicyGradient) | | | OK | -| [A2C](https://github.com/datawhalechina/easy-rl/tree/master/codes/A2C) | | | OK | -| [PPO](https://github.com/datawhalechina/easy-rl/tree/master/codes/PPO) | [PPO paper](https://arxiv.org/abs/1707.06347) | [PPO算法实战](https://blog.csdn.net/JohnJim0/article/details/115126363) | OK | -| DDPG | [DDPG Paper](https://arxiv.org/abs/1509.02971) | | OK | -| TD3 | [Twin Dueling DDPG Paper](https://arxiv.org/abs/1802.09477) | | | +| 算法名称 | 相关论文材料 | 环境 | 备注 | +| :--------------------------------------: | :---------------------------------------------------------: | ------------------------------------- | :--------------------------------: | +| [On-Policy First-Visit MC](../codes/MonteCarlo) | | [Racetrack](../codes/envs/racetrack_env.md) | | +| [Q-Learning](../codes/QLearning) | | [CliffWalking-v0](../codes/envs/gym_info.md) | | +| [Sarsa](../codes/Sarsa) | | [Racetrack](../codes/envs/racetrack_env.md) | | +| [DQN](../codes/DQN) | [DQN-paper](https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf) | [CartPole-v0](../codes/envs/gym_info.md) | | +| DQN-cnn | [DQN-paper](https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf) | [CartPole-v0](../codes/envs/gym_info.md) | 与DQN相比使用了CNN而不是全链接网络 | +| [DoubleDQN](../codes/DoubleDQN) | | [CartPole-v0](../codes/envs/gym_info.md) | 效果不好，待改进 | +| Hierarchical DQN | [Hierarchical DQN](https://arxiv.org/abs/1604.06057) | | | +| [PolicyGradient](../codes/PolicyGradient) | | [CartPole-v0](../codes/envs/gym_info.md) | | +| A2C | | [CartPole-v0](../codes/envs/gym_info.md) | | +| A3C | | | | +| SAC | | | | +| [PPO](../codes/PPO) | [PPO paper](https://arxiv.org/abs/1707.06347) | [CartPole-v0](../codes/envs/gym_info.md) | | +| DDPG | [DDPG Paper](https://arxiv.org/abs/1509.02971) | [Pendulum-v0](../codes/envs/gym_info.md) | | +| TD3 | [Twin Dueling DDPG Paper](https://arxiv.org/abs/1802.09477) | | | +| GAIL | | | | ## 贡献者 @@ -63,7 +66,7 @@ pic
John Jim -

项目设计
北京大学

+

算法实战
北京大学