BetaRare
datawhalechina/agentic-rl-lab
Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld and beyond.
- Owner
- datawhalechina (organization)
- Stars
- Stars: 853
- Forks
- Forks: 54
- Language
- Python
- License
- Apache-2.0
- Created
- 2026
- Topics
- agent-rldapogspoopdopsdpytrioretoolsearch-r1harness-rlalfworld
- Tier
- Beta (700 to 1,999 ★) What this tier means
More repos by datawhalechina
All 118 repos by datawhalechina- datawhalechina/hello-agentsStars: 85,835PythonLTS
- datawhalechina/happy-llmStars: 34,732Jupyter NotebookLTS
- datawhalechina/self-llmStars: 32,679Jupyter NotebookLTS
- datawhalechina/pumpkin-bookStars: 26,150LTS
- datawhalechina/llm-cookbookStars: 24,862Jupyter NotebookLTS
- datawhalechina/easy-vibeStars: 20,307JavaScriptLTS
Nearby in Python
All Python repos- Chuny1/3DGPTStars: 853PythonBeta
- OSU-NLP-Group/SeeActStars: 853PythonBeta
- jiayev/GPT4V-Image-CaptionerStars: 853PythonBeta
- CriticMarkup/CriticMarkup-toolkitStars: 853PythonBeta
- yukinarit/pyserdeStars: 853PythonBeta
- toddrob99/MLB-StatsAPIStars: 853PythonBeta