FLAIROx/Kinetix

Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.

45
/ 100
Emerging

Kinetix helps researchers and robotics engineers train intelligent agents in a simulated 2D physics environment. It takes descriptions of rigid-body physics tasks, which can be procedurally generated, and outputs agents capable of performing complex physical interactions, like grasping or navigating. This is ideal for those exploring how to build general-purpose reinforcement learning models that can adapt to new physical challenges.

234 stars.

Use this if you are a machine learning researcher or robotics engineer developing and testing reinforcement learning agents that need to interact with physics-based scenarios.

Not ideal if you are looking for a pre-built solution for a specific real-world robotic task or if you don't have a background in reinforcement learning and JAX.

robotics simulation reinforcement learning research agent training physics-based AI procedural environment generation
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

234

Forks

10

Language

Python

License

MIT

Last pushed

Feb 26, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/FLAIROx/Kinetix"

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