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.

PythonStars 529Forks 108Watchers 529Open issues 28License MIT License
Details
仓库信息
Ownerfacebookresearch
Last pushed2025-11-10
Last updated2025-12-14
Issues fetched at

Stats

Community at a glance

Loading...

Loading

--

Loading

--

Loading

--

Loading

--