BenchMARL: Benchmarking Multi-Agent Reinforcement Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bettini, Matteo, Prorok, Amanda, Moens, Vincent
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910711158931456
author Bettini, Matteo
Prorok, Amanda
Moens, Vincent
author_facet Bettini, Matteo
Prorok, Amanda
Moens, Vincent
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2312_01472
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle BenchMARL: Benchmarking Multi-Agent Reinforcement Learning
Bettini, Matteo
Prorok, Amanda
Moens, Vincent
Machine Learning
Artificial Intelligence
Multiagent Systems
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
title BenchMARL: Benchmarking Multi-Agent Reinforcement Learning
topic Machine Learning
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2312.01472