BenchMARL
by facebookresearch (organization)
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization. (description from the project’s GitHub page)
Repository facts
- Stars
- 675
- Forks
- 141
- Open issues and pull requests
- 39
- Primary language
- Python
- License
- MIT License (MIT)
- Owner
- facebookresearch · Organization
- Created
- Aug 22, 2023
- Last push
- Feb 7, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 2,180: pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
3,604 starsPythonMITLast push Oct 18, 2026
Rank 5,733: Toni-SM/skrl
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environmen…
1,101 starsPythonMITLast push Oct 18, 2026
Rank 7,452: Stable-Baselines-Team/stable-baselines3-contrib
Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
740 starsPythonMITLast push Oct 16, 2026
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
Rank 6,827: OpenRL-Lab/openrl
Unified Reinforcement Learning Framework
844 starsPythonApache-2.0Last push Sep 6, 2024
Rank 2,721: DLR-RM/rl-baselines3-zoo
A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
2,897 starsPythonMITLast push Oct 16, 2026