ResearchBenchmarksMulti-Agent Reinforcement Learning on MPE World ExpertFollow91.8Mean Episode ReturnDOM249.47260.46171.4582.439Jul 4, 2023Evaluation ResultsMethodMethodLinksMean Episode ReturnDOM22023.0791.8MA-SfBC2023.0782OMAR2023.0771.1MA-CQL2023.0751.1