Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.
| Date | Stars |
|---|---|
| 2026-07-31 | 263 |
| 2026-08-03 | 264 |
| 2026-08-06 | 264 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="middle">
<img src="https://raw.githubusercontent.com/FlairOX/Kinetix/main/images/kinetix_logo.gif" width="500" />
</p>
<p align="center">
<a href= "https://pypi.org/project/jax2d/">
<img src="https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue" /></a>
<a href= "https://pypi.org/project/kinetix-env/">
<img src="https://img.shields.io/badge/pypi-1.0.0-green" /></a>
<a href= "https://github.com/FLAIROx/Kinetix/blob/main/LICENSE">
<img src="https://img.shields.io/badge/License-MIT-yellow" /></a>
<a href= "https://github.com/psf/black">
<img src="https://img.shields.io/badge/code%20style-black-000000.svg" /></a>
<a href= "https://kinetix-env.github.io/">
<img src="https://img.shields.io/badge/online-editor-purple" /></a>
<a href= "https://arxiv.org/abs/2410.23208">
<img src="https://img.shields.io/badge/arxiv-2410.23208-b31b1b" /></a>
<a href= "./docs/README.md">
<img src="https://img.shields.io/badge/docs-green" /></a>
<a href= "https://huggingface.co/datasets/mbeukman/Kinetix-Offline">
<img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Dataset-ffcc66" /></a>
</p>
### <b>Update: We've released a large offline dataset of expert trajectories [here](https://huggingface.co/datasets/mbeukman/Kinetix-Offline)!</b>
# Kinetix
Kinetix is a framework for reinforcement learning in a 2D rigid-body physics world, written entirely in [JAX](https://github.com/jax-ml/jax).
Kinetix can represent a huge array of physics-based tasks within a unified framework.
We use Kinetix to investigate the training of large, general reinforcement learning agents by procedurally generating millions of tasks for training.
You can play with Kinetix in our [online editor](https://kinetix-env.github.io/gallery.html?editor=true), or have a look at the JAX [physics engine](https://github.com/MichaelTMatthews/Jax2D) and [graphics library](https://github.com/FLAIROx/JaxGL) we made for Kinetix. Finally, see our [docs](./docs/README.md) for more information and more in-depth examples.
<p align="middle">
<img src="https://raw.githubusercontent.com/FlairOX/Kinetix/main/images/bb.gif" width="200" />
<img src="https://raw.githubusercontent.com/FlairOX/Kinetix/main/images/cartpole.gif" width="200" />
<img src="https://raw.githubusercontent.com/FlairOX/Kinetix/main/images/grasper.gif" width="200" />
</p>
<p align="middle">
<img src="https://raw.githubusercontent.com/FlairOX/Kinetix/main/images/hc.gif" width="200" />
<img src="https://raw.githubusercontent.com/FlairOX/Kinetix/main/images/hopper.gif" width="200" />
<img src="https://raw.githubusercontent.com/FlairOX/Kinetix/main/images/ll.gif" width="200" />
</p>
<p align="middle">
<b>The above shows specialist agents trained on their respective levels.</b>
</p>
# 📊 Paper TL; DR
We train a general agent on millions of procedurally generated physics tasks.
Every task has the same goal: make the <span style="color:green">green</span> and <span style="color:blue">blue</span> touch, without <span style="color:green">green</span> touching <span style="color:red">red</span>.
The agent can act through applying torque via motors and force via thrusters.
<p align="middle">
<img src="https://raw.githubusercontent.com/FlairOX/Kinetix/main/images/random_1.gif" width="200" />
<img src="https://raw.githubusercontent.com/FlairOX/Kinetix/main/images/random_5.gif" width="200" />
<img src="https://raw.githubusercontent.com/FlairOX/Kinetix/main/images/random_3.gif" width="200" />
</p>
<p align="middle">
<img src="https://raw.githubusercontent.com/FlairOX/Kinetix/main/images/random_4.gif" width="200" />
<img src="https://raw.githubusercontent.com/FlairOX/Kinetix/main/images/random_6.gif" width="200" />
<img src="https://raw.githubusercontent.com/FlairOX/Kinetix/main/images/random_7.gif" width="200" />
</p>
<p align="middle">
<b>The above showsExcerpt of 16,818 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c3dcc00c45860098, topic:reinforcement-learning, desc:reinforcement learning