ResearchBenchmarksMulti-agent Reinforcement Learning on MPE Prey-and-Predator (Random)Multi-agent Reinforcement Learning on MPE Prey-and-Predator (Random)Follow30.3Average Normalized ScoreMACCA-ICQ4.50811.20417.924.596Dec 6, 2023Evaluation resultsMethodMethodLinksAverage Normalized ScoreMACCA-ICQBackbone=ICQBackbone=ICQ2023.1230.3MACCA-OMARBackbone=OMARBackbone=OMAR2023.1220.9MA-ICQ2023.1215.6MACCA-CQLBackbone=CQLBackbone=CQL2023.1214.7OMAR2023.1212I-CQL2023.125.5