# datawhalechina/agentic-rl-lab

<https://repo.masters-masters.com/en/repos/datawhalechina/agentic-rl-lab>

[Home](https://repo.masters-masters.com/en) › [datawhalechina](https://repo.masters-masters.com/en/owners/datawhalechina) › [agentic-rl-lab](https://repo.masters-masters.com/en/repos/datawhalechina/agentic-rl-lab)

datawhalechina/agentic-rl-lab has 1,098 stars on GitHub. Its RepoMasters card: Beta tier. Reproducing and studying RL algorithms for LLM agents, including…

| Field | Value |
| --- | --- |
| Owner | [datawhalechina](https://repo.masters-masters.com/en/owners/datawhalechina) |
| Stars | 1,098 |
| Forks | 69 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | Apache-2.0 |
| Created | 2026 |
| Topics | agent-rl, dapo, gspo, opd, opsd, pytrio, retool, search-r1, harness-rl, alfworld |
| Tier | [Beta (700 to 1,999 ★)](https://repo.masters-masters.com/en/ranks/box_office) |
| View on GitHub | [datawhalechina/agentic-rl-lab](https://github.com/datawhalechina/agentic-rl-lab) |

## Repository

Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld and beyond.

The tier for repos with 700 to 1,999 ★. Published odds per card pulled: 6%. Rarity: Rare.

## More repos by datawhalechina

- [datawhalechina/hello-agents · ★ 85,973 · Python · LTS](https://repo.masters-masters.com/en/repos/datawhalechina/hello-agents)
- [datawhalechina/happy-llm · ★ 34,753 · Jupyter Notebook · LTS](https://repo.masters-masters.com/en/repos/datawhalechina/happy-llm)
- [datawhalechina/self-llm · ★ 32,700 · Jupyter Notebook · LTS](https://repo.masters-masters.com/en/repos/datawhalechina/self-llm)
- [datawhalechina/pumpkin-book · ★ 26,151 · LTS](https://repo.masters-masters.com/en/repos/datawhalechina/pumpkin-book)
- [datawhalechina/llm-cookbook · ★ 24,870 · Jupyter Notebook · LTS](https://repo.masters-masters.com/en/repos/datawhalechina/llm-cookbook)
- [datawhalechina/easy-vibe · ★ 20,330 · JavaScript · LTS](https://repo.masters-masters.com/en/repos/datawhalechina/easy-vibe)

## Nearby in Python

- [jacobgil/vit-explain · ★ 1,098 · Python · Beta](https://repo.masters-masters.com/en/repos/jacobgil/vit-explain)
- [N0rz3/Zehef · ★ 1,098 · Python · Beta](https://repo.masters-masters.com/en/repos/N0rz3/Zehef)
- [minghanqin/LangSplat · ★ 1,098 · Python · Beta](https://repo.masters-masters.com/en/repos/minghanqin/LangSplat)
- [coderholic/pyradio · ★ 1,098 · Python · Beta](https://repo.masters-masters.com/en/repos/coderholic/pyradio)
- [lepture/captcha · ★ 1,098 · Python · Beta](https://repo.masters-masters.com/en/repos/lepture/captcha)
- [sideeffects/GameDevelopmentToolset · ★ 1,098 · Python · Beta](https://repo.masters-masters.com/en/repos/sideeffects/GameDevelopmentToolset)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.