ResearchBenchmarksMulti-Agent Reinforcement Learning on MPE Cooperative Navigation Random MediumFollow304.5Mean Episode ReturnDOM2169.092204.246239.4274.554Jul 4, 2023Evaluation ResultsMethodMethodLinksMean Episode ReturnDOM22023.07304.5OMAR2023.07266.1MA-CQL2023.07251MA-SfBC2023.07174.3