#5454th of 88 in Learning and cookbooks
agentic-rl-lab
Tutorials and runnable code for reproducing LLM and agent RL algorithms
- Stars
- 1.4k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Language
- Python
15 on 7 Jul 20261,375 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A Chinese-first tutorial repository (English edition available) that explains and reproduces about 17 RL methods for LLMs and agents, including GRPO, GSPO, DAPO, OPD/OPSD, Search-R1, ReTool, ALFWorld and Vision GRPO. Each chapter ships data, reward, loss and training-loop code. Training runs through the PyTRIO remote Train API and is logged to SwanLab. The README says the getting-started path needs no local GPU.
Who it is for: Learners and researchers running agentic RL without multi-GPU clusters
Strengths
- Covers many methods: GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld, TEMPO
- Training runs remotely through PyTRIO, so no local multi-GPU setup is needed
- Each chapter pairs an online write-up with code and SwanLab logging
- Pinned dependencies (pytrio 0.2.9, swanlab 0.10.4) and uv-based install
Weaknesses
- Depends on the hosted PyTRIO service and an account for training
- Chapters are per-experiment scripts, not a reusable training framework
- Main README is in Chinese; English edition is a separate file
- ALFWorld, TEMPO and AgentOPSD need an extra TextWorld install
What it needs
- no GPU
- Needs PyTRIO, SwanLab, uv, DeepSeek Search API (Search-R1), TextWorld (ALFWorld, TEMPO, AgentOPSD)
- Models: Qwen3.5-4B, Qwen3.5-9B
Quick answers
Is agentic-rl-lab open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Does agentic-rl-lab need a GPU?
No, it runs without one.
Also in Learning and cookbooks
See all 88| 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 | 81 out of 100 |
| #4 | cs249r_bookOpen textbook and course materials for machine learning systems engineering | 81 out of 100 |
| #5 | ai-for-beginners24-lesson AI curriculum with notebooks in PyTorch and TensorFlow | 80 out of 100 |