ResearchBenchmarksMulti-agent Reinforcement Learning on MPE Simple-World Medium-ReplyMulti-agent Reinforcement Learning on MPE Simple-World Medium-ReplyFollow50.9Average Normalized ScoreMACCA-OMAR2.64415.17227.740.228Dec 6, 2023Evaluation resultsMethodMethodLinksAverage Normalized ScoreMACCA-OMARBackbone=OMARBackbone=OMAR2023.1250.9MACCA-ICQBackbone=ICQBackbone=ICQ2023.1239.9MACCA-CQLBackbone=CQLBackbone=CQL2023.1234.8OMAR2023.1228.9MA-ICQ2023.1210.7I-CQL2023.124.5