AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library

Siyi Hu, Yifan Zhong, Minquan Gao, Weixun Wang, Hao Dong, Xiaodan Liang, Zhihui Li, Xiaojun Chang, Yaodong Yang

JMLR 2023 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Cooperative MARL algorithms · 33 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use MARLlib (Ray/RLlib workers) instead of EPyMARLMAPPO training · SMAC MMM2, 15 workersclock time (min:sec): 2:24 -> 1:24Improved
use MARLlib instead of official MAPPOMAPPO training · SMAC MMM2, 5 workersclock time (min:sec): 5:12 -> 3:29Improved
use MARLlib instead of EPyMARLMAPPO training · SMAC MMM2, 10 workersclock time (min:sec): 3:14 -> 2:16Improved
use MARLlib instead of EPyMARLMAPPO training · SMAC MMM2, 15 workersmemory (GB): 15.8 -> 20.4Hurt
use MARLlib instead of EPyMARLMAPPO training · SMAC MMM2, 5 workersGPU memory (MB): 2245 -> 5025Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy