roboterax/humanoid-gym

Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer https://arxiv.org/abs/2404.05695

40
/ 100
Emerging

This project helps robotics engineers and researchers train bipedal humanoid robots to walk and move in the real world. You input your robot's design and receive optimized control policies that enable complex locomotion. It's designed for professionals working on advanced robot development and deployment.

1,894 stars. No commits in the last 6 months.

Use this if you need to quickly train humanoid robots for real-world tasks using advanced simulation and ensure their behavior transfers directly without extensive real-world tuning.

Not ideal if you are working with non-humanoid robots or require a different simulation environment than Nvidia Isaac Gym and Mujoco.

humanoid-robotics robot-locomotion reinforcement-learning sim2real-transfer robot-development
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 22 / 25

How are scores calculated?

Stars

1,894

Forks

248

Language

Python

License

Last pushed

Jan 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/roboterax/humanoid-gym"

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