xf-zhao/Agentic-Skill-Discovery

Official implementation of Zero-Hero paper

24
/ 100
Experimental

This project helps robotics engineers and researchers rapidly develop and test new robot behaviors for complex tasks. By providing a high-level description of a desired task and the robot's environment, it automatically generates specific sub-tasks and trains reinforcement learning policies to execute them. The output is a robust, learned robot policy that can perform the described actions within a simulated environment.

No commits in the last 6 months.

Use this if you need to quickly teach robots new skills for a variety of tasks in a simulated environment, using natural language descriptions.

Not ideal if you are looking for a solution for real-world robot deployment without prior simulation or if you require fine-grained, manual control over every aspect of policy development.

robotics development reinforcement learning task automation robot simulation AI for robotics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

29

Forks

3

Language

Python

License

Last pushed

Feb 13, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/xf-zhao/Agentic-Skill-Discovery"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.