ResearchBenchmarksMulti-Agent Reinforcement Learning on MPE World Random MediumFollow30.3Mean Episode ReturnDOM2-7.4522.34912.1521.951Jul 4, 2023Evaluation ResultsMethodMethodLinksMean Episode ReturnDOM22023.0730.3OMAR2023.0728.7MA-SfBC2023.070MA-CQL2023.07-6