ResearchBenchmarksOffline Multi-Agent Reinforcement Learning on SMAC 6h_vs_8z (good-poor)Offline Multi-Agent Reinforcement Learning on SMAC 6h_vs_8z (good-poor)Follow11.88Average ScoreOMIGA9.06169.793310.52511.2567Jul 21, 2023Evaluation resultsMethodMethodLinksAverage ScoreOMIGArandom seeds=5random seeds=52023.0711.88BCQ-MArandom seeds=5random seeds=52023.0711.41ICQrandom seeds=5random seeds=52023.0711CQL-MArandom seeds=5random seeds=52023.079.56OMARrandom seeds=5random seeds=52023.079.17