ResearchBenchmarksMulti-Agent Reinforcement Learning on MPE Cooperative Navigation (Medium Replay)Follow302.1Mean Episode ReturnDOM2187.492217.246247276.754Jul 4, 2023Evaluation ResultsMethodMethodLinksMean Episode ReturnDOM22023.07302.1OMAR2023.07271.3MA-CQL2023.07224.2MA-SfBC2023.07191.9