#3939th of 41 in Learning and cookbooks
easy-rl
Chinese-language reinforcement learning textbook with Jupyter notebook implementations
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 14.8k
- License
- custom license
- Last commit
- Dec 2025
- Last release
- Jul 2023
- Language
- Jupyter Notebook
13,775 on 31 Mar 202614,818 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
"Mushroom Book" (蘑菇书) is a Chinese reinforcement learning tutorial built from Hung-yi Lee's deep RL lectures, Bolei Zhou's RL course notes and Baidu's hands-on RL course. It has 13 chapters with exercises, plus notebooks for Q-learning, Sarsa, Monte Carlo, policy gradient, PPO, DQN variants, A2C and DDPG. Content is readable online and as a PDF, and a print edition exists.
Who it is for: Chinese-reading learners starting reinforcement learning
Strengths
- Runnable notebooks for policy gradient, PPO, DQN variants, A2C and DDPG
- Chapters include exercises and a public errata page
- Free online version and PDF releases, plus a printed edition
- Includes paper walkthroughs and links to JoyRL code
Weaknesses
- Text is in Chinese only; the README mentions no English edition
- License is CC BY-NC-SA 4.0, which bars commercial use
- Last tagged release is from 2023-07-25
- Chapters 8, 10 and 11 have no companion code listed
Also in Learning and cookbooks
See all 41| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on AI engineering curriculum with 542 lessons across 20 phases | 89 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 81 out of 100 |
| 3 | ai-agents-for-beginners18-lesson course on building AI agents with Microsoft Agent Framework | 78 out of 100 |
| #4 | llms-from-scratchCode for the book on building a GPT-style LLM in PyTorch | 77 out of 100 |
| #5 | ml-for-beginners12-week, 26-lesson classic machine learning course using Scikit-learn | 76 out of 100 |