ResearchBenchmarksMulti-Agent Reinforcement Learning on MPE World (Random)Multi-Agent Reinforcement Learning on MPE World (Random)Follow35.6Mean Episode ReturnDOM2-4.2326.10916.4526.791Jul 4, 2023Evaluation resultsMethodMethodLinksMean Episode ReturnDOM22023.0735.6OMAR2023.071.1MA-SfBC2023.07-1.9MA-CQL2023.07-2.7