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 systematically grounded in its two core tenets: reproducibility and standardization.

69
/ 100
Established

BenchMARL helps machine learning researchers compare different Multi-Agent Reinforcement Learning (MARL) algorithms. You input various algorithms, environments, and models, and it systematically generates standardized performance metrics and plots for fair comparison. It's designed for researchers evaluating their novel MARL approaches against existing solutions or exploring the current landscape of MARL techniques.

580 stars. Available on PyPI.

Use this if you need to reliably benchmark and compare the performance of different multi-agent reinforcement learning algorithms or models across various simulated environments.

Not ideal if you are looking for a general-purpose reinforcement learning library for single-agent tasks or if you don't require standardized, reproducible comparisons for research.

multi-agent-reinforcement-learning algorithm-benchmarking AI-research simulation-testing model-evaluation
Maintenance 10 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 24 / 25

How are scores calculated?

Stars

580

Forks

117

Language

Python

License

MIT

Last pushed

Feb 07, 2026

Commits (30d)

0

Dependencies

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/facebookresearch/BenchMARL"

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