#4343rd of 100 in Learning and cookbooks
hands-on-modern-rl
Open course teaching RL from CartPole and DQN to RLHF, GRPO and agents
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 4.6k
- License
- custom license
- Last commit
- Oct 2026
- Last release
- Jun 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
A bilingual (English/Chinese) online book and code collection that teaches RL in 26 chapters, from MDPs, DQN, policy gradients and PPO to DPO, GRPO, verifiable rewards, agentic RL and VLM training. It ships runnable scripts (SB3, veRL, EasyR1), 14 chapter notebooks, and ModelScope Studio companions for browser-based classic RL experiments. The authors say it was created with AI assistance and is not fully reviewed.
Who it is for: Engineers and students learning RL and LLM post-training by running code
Strengths
- Covers classic RL through RLHF, DPO, GRPO and agentic RL in one sequence
- Runnable examples: CartPole, Atari Pong, LunarLander, BipedalWalker, DPO, code RLVR, GeoQA
- Online ModelScope Studios and companion notebooks allow training without local setup
- English and Chinese editions, with PDF builds released via CI
Weaknesses
- README says content is AI-assisted and not fully reviewed; code may not run as expected
- Some chapters are still under construction and may contain mistakes
- Online experiments depend on ModelScope; five need a scheduled xGPU notebook
- Content is CC BY-NC-SA 4.0, which restricts commercial use
What it needs
- GPU optional
- Needs ModelScope, Stable-Baselines3, veRL, EasyR1, Gymnasium, Node >= 18 (VitePress docs)
Also in Learning and cookbooks
See all 100| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on AI engineering curriculum with 542 lessons across 20 phases | 91 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 83 out of 100 |
| 3 | rag_techniquesCollection of 42 runnable notebooks implementing RAG techniques | 82 out of 100 |
| #4 | cs249r_bookOpen textbook and course materials for machine learning systems engineering | 82 out of 100 |
| #5 | ai-for-beginners24-lesson AI curriculum with notebooks in PyTorch and TensorFlow | 81 out of 100 |