ResearchBenchmarksMulti-agent Reinforcement Learning on MPE Cooperative Navigation RandomMulti-agent Reinforcement Learning on MPE Cooperative Navigation RandomFollow337.8Average Normalized ScoreDOM2-7.27282.314171.9261.486Jul 4, 2023Jul 29, 2023Aug 24, 2023Sep 19, 2023Oct 15, 2023Nov 10, 2023Dec 6, 2023Evaluation resultsMethodMethodLinksAverage Normalized ScoreDOM22023.07337.8OMAR2023.07211.3MA-CQL2023.07206MA-SfBC2023.07179.8MACCA-OMARBackbone=OMARBackbone=OMAR2023.1232.8MACCA-ICQBackbone=ICQBackbone=ICQ2023.1228.13OMAR2023.1222.9MACCA-CQLBackbone=CQLBackbone=CQL2023.1222.2I-CQL2023.1212.4MA-ICQ2023.126