offworld-projects/offworld-gym

OffWorld Gym: Open-Access Physical Robotics Environment for Real-World Reinforcement Learning Benchmark and Research

38
/ 100
Emerging

OffWorld Gym provides free remote access to real-world robotic environments for training and testing reinforcement learning algorithms. Researchers can connect their algorithms to physical wheeled robots on uneven terrain, using camera images (RGB/Depth) as input to control robot movement. This service is designed for reinforcement learning researchers who need to validate their agents in a physical setting.

No commits in the last 6 months.

Use this if you are a reinforcement learning researcher who wants to test your algorithms on real robots without managing physical hardware.

Not ideal if you are looking for a simulated-only environment or if you do not have prior experience with reinforcement learning frameworks.

robotics research reinforcement learning robot control AI experimentation real-world AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

57

Forks

8

Language

Python

License

GPL-3.0

Last pushed

May 22, 2023

Commits (30d)

0

Get this data via API

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

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