FLAIROx / Kinetix
Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.
Why this job: says: reinforcement learning; topics: reinforcement-learning
What it does
Kinetix is a framework for reinforcement learning in a 2D rigid-body physics world, written entirely in 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, or have a look at the JAX physics engine and graphics library we made for Kinetix. Finally, see our docs for more information and more in-depth examples.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 47 days ago
- Stars
- 285
- +3 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v3.0.2
- Released 47 days ago
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 92% closed
- 1 still open
- Pull requests
- 27 merged
- 0 waiting
- Releases
- 7
- 2 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| alessiodm / drl-zh | 2,293 | 5 months ago | MIT | No downloads |
| G-U-N / UniRL | 102 | 5 months ago | Apache-2.0 | No downloads |
| Infini-AI-Lab / astraflow | 114 | 3 months ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- machine-learning
- physics-engine
- reinforcement-learning
Project record
- JobFine-tuning
- StatusListed
- Commits44
- Forks14
- Watching7
- Stars in 28 days+9
- CreatedNov 6, 2024
- First seen by usNov 7, 2026
- CheckedNov 10, 2026
