ResearchBenchmarksOffline Multi-Agent Reinforcement Learning on SMAC 6h_vs_8z (medium-poor)Offline Multi-Agent Reinforcement Learning on SMAC 6h_vs_8z (medium-poor)Follow11.85Average ScoreOMIGA10.362810.748911.13511.5211Jul 21, 2023Evaluation resultsMethodMethodLinksAverage ScoreOMIGArandom seeds=5random seeds=52023.0711.85ICQrandom seeds=5random seeds=52023.0711.25BCQ-MArandom seeds=5random seeds=52023.0711.18CQL-MArandom seeds=5random seeds=52023.0710.73OMARrandom seeds=5random seeds=52023.0710.42