FLAIROx/Kinetix
Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.
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.
Stars
234
Forks
10
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
explosion/thinc
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
google-deepmind/optax
Optax is a gradient processing and optimization library for JAX.
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable....
google/grain
Library for reading and processing ML training data.
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/