ResearchBenchmarksOffline Multi-Agent Reinforcement Learning on SMAC corridor (good-poor)Offline Multi-Agent Reinforcement Learning on SMAC corridor (good-poor)Follow13.01Average ScoreOMIGA4.55486.74998.94511.1401Jul 21, 2023Evaluation resultsMethodMethodLinksAverage ScoreOMIGArandom seeds=5random seeds=52023.0713.01BCQ-MArandom seeds=5random seeds=52023.0712.37ICQrandom seeds=5random seeds=52023.0711.78OMARrandom seeds=5random seeds=52023.075.54CQL-MArandom seeds=5random seeds=52023.074.88