ResearchBenchmarksMulti-Agent Reinforcement Learning on MPE Cooperative Navigation Medium ExpertFollow439.6Mean Episode ReturnDOM2271.432315.091358.75402.409Jul 4, 2023Evaluation ResultsMethodMethodLinksMean Episode ReturnDOM22023.07439.6OMAR2023.07373.9MA-CQL2023.07279.9MA-SfBC2023.07277.9