by xf-zhao · Agent Tool · ★ 29
Official Implementation of Agentic Skill Discovery (ASD) This is the official implementation of agentic skill discovery, a framework driven by LLMs to generate task proposals based on the scene description and the robot's configurations. For each task, reinforcement learning processes, guided by LLM-derived success and reward functions, develop the necessary policies. An independent vision-language model ensures the reliability of learned behaviors. The simulation is based on Isaac-sim.
| Stars | 29 |
| Forks | 3 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 69.6764635418683/100 |
| Open Issues | 1 |
| Last Updated | 2025-02-13 |
| Created | 2024-01-08 |
| Platforms | python |
| Est. Tokens | ~577k |
Explore other popular agent tool tools:
Agentic-Skill-Discovery is Official implementation of Zero-Hero paper. It is categorized as a Agent Tool with 29 GitHub stars.
Agentic-Skill-Discovery is primarily written in Python. It covers topics such as agentic, agentic-ai, llm.
You can find installation instructions and usage details in the Agentic-Skill-Discovery GitHub repository at github.com/xf-zhao/Agentic-Skill-Discovery. The project has 29 stars and 3 forks, indicating an active community.