JaxMARL

Repository facts

Stars

859

Forks

162

Open issues and pull requests

15

Primary language

Python

License

Apache License 2.0 (Apache-2.0)

Owner

bold-lab-ai · Organization

Created

Mar 27, 2023

Last push

Sep 10, 2026

Topics

• marl
• multiagent-reinforcement-learning
• reinforcement-learning

Rank #6,743 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Related projects

Projects that share this one’s GitHub topics.

• 2,152

  Rank 2,152: opendilab/DI-engine

  OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

  3,649 starsPythonApache-2.0Last push Dec 7, 2025

• 2,216

  Rank 2,216: Farama-Foundation/PettingZoo

  A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities

  3,535 starsPythonMITLast push Oct 9, 2026

• 2,180

  Rank 2,180: pytorch/rl

  A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

  3,604 starsPythonMITLast push Oct 18, 2026

• 6,360

  Rank 6,360: instadeepai/Mava

  🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

  938 starsPythonApache-2.0Last push Sep 9, 2026

• 7,671

  Rank 7,671: hijkzzz/pymarl2

  Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)

  710 starsPythonApache-2.0Last push May 18, 2024

• 7,917

  Rank 7,917: facebookresearch/BenchMARL

  BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being sys…

  675 starsPythonMITLast push Feb 7, 2026