https://github.com/AmazingAng/WTF-DeepRL

Deep RL algorithm in pytorch
https://github.com/AmazingAng/WTF-DeepRL

Last synced: 3 months ago
JSON representation

Deep RL algorithm in pytorch

• Host: GitHub
• URL: https://github.com/AmazingAng/WTF-DeepRL
• Owner: AmazingAng
• Created: 2020-04-09T08:46:19.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2023-09-05T07:09:18.000Z (about 1 year ago)
• Last Synced: 2024-07-27T21:40:45.104Z (3 months ago)
• Language: Jupyter Notebook
• Size: 2.83 MB
• Stars: 281
• Watchers: 4
• Forks: 54
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-ChatGPT-repositories - deep-RL-elements - Deep RL algorithm in pytorch (Others)

README

        
# WTF 深度强化学习

WTF 深度强化学习算法库及教程，学习并复现经典的深度强化学习算法。

深度强化学习算法使用pytorch实现，写在jupyter notebook中。用Atari Games中的Pong测试。

## 先修课程

1. 机器学习/深度学习

2. python编程

3. 经典强化学习

## 目录

**第1讲：Deep Q-learning**：[文章](https://github.com/AmazingAng/WTF-DeepRL/tree/master/01_DQN/readme.md) | [Code](https://github.com/AmazingAng/WTF-DeepRL/tree/master/01_DQN) | [Google Colab](https://colab.research.google.com/github/AmazingAng/WTF-DeepRL/blob/master/01_DQN/DQN.ipynb#)

**第2讲：Prioritized Experience Replay (PER)**：[代码](https://github.com/AmazingAng/deep-RL-elements/tree/master/02_DQN_PER) | [文章](https://github.com/AmazingAng/deep-RL-elements/tree/master/02_DQN_PER/readme.md)

**第3讲：Double DQN (DDQN)**：[代码](https://github.com/AmazingAng/deep-RL-elements/tree/master/03_DDQN) | [文章](https://github.com/AmazingAng/deep-RL-elements/tree/master/03_DDQN/readme.md)

**第4讲：Dueling DQN**：[代码](https://github.com/AmazingAng/deep-RL-elements/tree/master/04_DuelingDQN) | [文章](https://github.com/AmazingAng/deep-RL-elements/tree/master/04_DuelingDQN/readme.md)

**第5讲：DQN with Soft Update (Soft DQN)**：[代码](https://github.com/AmazingAng/deep-RL-elements/tree/master/05_SoftDQN) | [文章](https://github.com/AmazingAng/deep-RL-elements/tree/master/readme.md)

**第6讲：DQN with Noisy Net**：[代码](https://github.com/AmazingAng/deep-RL-elements/tree/master/06_NoisyDQN) | [文章](https://github.com/AmazingAng/deep-RL-elements/tree/master/readme.md)

**第7讲：DQN with Intrinsic Curiosity Module**：[代码](https://github.com/AmazingAng/deep-RL-elements/tree/master/07_ICMDQN) | [文章](https://github.com/AmazingAng/deep-RL-elements/tree/master/07_ICMDQN/readme.md)

**第8讲：Deep Recurrent Q-learning (DRQN)**：[代码](https://github.com/AmazingAng/deep-RL-elements/tree/master/08_DRQN) | [文章](https://github.com/AmazingAng/deep-RL-elements/tree/master/08_DRQN/readme.md)

**第9讲：N-step DQN**：[代码](https://github.com/AmazingAng/deep-RL-elements/tree/master/09_NStepDQN) | [文章](https://github.com/AmazingAng/deep-RL-elements/tree/master/09_NStepDQN/readme.md)

## Prerequisite 

- torch 1.4.0

- gym[atari]

- tensorboardX 

## 其他深度强化学习算法库 (pytorch)

- [Reinforcement-Learning](https://github.com/andri27-ts/Reinforcement-Learning)

- [DeepRL-Tutorials](https://github.com/qfettes/DeepRL-Tutorials)

- [Deep-Reinforcement-Learning-Algorithms-with-PyTorch](https://github.com/p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch)