BenchMARL: Benchmarking Multi-Agent Reinforcement Learning

Matteo Bettini, Amanda Prorok, Vincent Moens
12/3/2023
cs.LGcs.AIcs.MA

Official code: facebookresearch/BenchMARL (675 stars, MIT, PyTorch, last commit 2026-02-07).

Abstract

The field of Multi-Agent Reinforcement Learning (MARL) is currently facing a reproducibility crisis. While solutions for standardized reporting have been proposed to address the issue, we still lack a benchmarking tool that enables standardization and reproducibility, while leveraging cutting-edge Reinforcement Learning (RL) implementations. In this paper, we introduce BenchMARL, the first MARL training library created to enable standardized benchmarking across different algorithms, models, and environments. BenchMARL uses TorchRL as its backend, granting it high performance and maintained state-of-the-art implementations while addressing the broad community of MARL PyTorch users. Its design enables systematic configuration and reporting, thus allowing users to create and run complex benchmarks from simple one-line inputs. BenchMARL is open-sourced on GitHub: https://github.com/facebookresearch/BenchMARL

View on arXivView PDF

Code Implementations(1)

facebookresearch/BenchMARLOfficial100%
PyTorchMIT

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.

675141Python, Jupyter NotebookAug 22, 20238 months agoMIT
benchmarkmachine-learningmarlmulti-agentmulti-agent-reinforcement-learning+5 more

Similar Papers

Flower Hub: A Reproducible Benchmarking Platform for Federated Learning in Simulation and Deployment

84% match2026

MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments

83% match2026

PaperGym: Rubric-Centered Evolution for Research-Plan Generation

83% match2026

Rollout Cards: A Reproducibility Standard for Agent Research

82% match2026

AlphaZero-Edu: Democratizing Access to AlphaZero

82% match1 repo52025

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents

82% match2026

Cite this paper

@article{bettini2023benchmarl,
  title  = {BenchMARL: Benchmarking Multi-Agent Reinforcement Learning},
  author = {Matteo Bettini and Amanda Prorok and Vincent Moens},
  year   = {2023},
  eprint = {2312.01472},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2312.01472v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2312.01472.svg)](https://codeofpaper.com/paper/2312.01472)

Discussion