by ZJU-REAL · Codex Skill · ★ 284
SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization 🔥 Overview We introduce SKILL0, an in-context reinforcement learning framework designed for skill internalization. SKILL0 achieves substantial improvements over the standard RL baseline on ALFWorld and Search-QA. 🗞️ News : 🔥🔥 Our new work was released: SDAR, which introduces Self-Distilled Agentic Reinforcement Learning. : 🔥 Our new work was released: SKILL1, which evloves skill-augmented agents in one unified policy. : We release our paper and code. 🛠️ Installation Python environment bash conda c
| Stars | 284 |
| Forks | 11 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 53.506/100 |
| Last Updated | 2026-05-20 |
| Created | 2026-04-02 |
| Platforms | python |
| Est. Tokens | ~2348k |
Explore other popular codex skill tools:
SkillZero is Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization". It is categorized as a Codex Skill with 284 GitHub stars.
SkillZero is primarily written in Python. It covers topics such as agent, curriculum-learning, in-context-reinforcement-learning.
You can find installation instructions and usage details in the SkillZero GitHub repository at github.com/ZJU-REAL/SkillZero. The project has 284 stars and 11 forks, indicating an active community.
SkillZero is released under the Apache-2.0 license, making it free to use and modify according to the license terms.