ResearchBenchmarksOffline Multi-Agent Reinforcement Learning on SMAC 6h_vs_8z (good-medium)Offline Multi-Agent Reinforcement Learning on SMAC 6h_vs_8z (good-medium)Follow12.05Average ScoreOMIGA9.938810.486911.03511.5831Jul 21, 2023Evaluation resultsMethodMethodLinksAverage ScoreOMIGArandom seeds=5random seeds=52023.0712.05BCQ-MArandom seeds=5random seeds=52023.0711.79ICQrandom seeds=5random seeds=52023.0711.18CQL-MArandom seeds=5random seeds=52023.0710.08OMARrandom seeds=5random seeds=52023.0710.02