gabe00122/jaxrl

Partially Observable Multi-Agent RL with Transformers

33
/ 100
Emerging

This project helps AI researchers and game developers create and train intelligent agents for complex multi-agent environments. It takes in environment definitions and training configurations, and outputs highly optimized agent policies capable of memory, planning, and cooperation. The primary users are researchers exploring advanced reinforcement learning techniques and developers building AI for games or simulations.

Use this if you are a researcher or developer focused on training AI agents that need to collaborate, remember past actions, and plan in environments where they can only see part of the world.

Not ideal if you are looking for a simple, out-of-the-box solution for single-agent or fully observable reinforcement learning tasks.

multi-agent-systems game-ai-development reinforcement-learning-research ai-simulation
No License No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

17

Forks

2

Language

Python

License

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/gabe00122/jaxrl"

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