BriefGPT.xyz
Dec, 2023
BenchMARL: 多智能体强化学习基准
BenchMARL: Benchmarking Multi-Agent Reinforcement Learning
HTML
PDF
Matteo Bettini, Amanda Prorok, Vincent Moens
TL;DR
多智能体强化学习领域面临再现性危机，本文引入BenchMARL作为第一个用于标准化基准测试的训练库，具备高性能和最新技术实现，从而满足多智能体PyTorch用户的需求。
Abstract
The field of
multi-agent reinforcement learning
(MARL) is currently facing a
reproducibility crisis
. While solutions for
standardized reporting
→