ResearchBenchmarksMulti-Agent Reinforcement Learning on MPE World Medium ExpertFollow79.9Mean Episode ReturnDOM237.67648.63859.670.562Jul 4, 2023Evaluation ResultsMethodMethodLinksMean Episode ReturnDOM22023.0779.9OMAR2023.0744.6MA-CQL2023.0740.9MA-SfBC2023.0739.3