ResearchBenchmarksOffline Multi-Agent Reinforcement Learning on SMAC corridor (medium-poor)Offline Multi-Agent Reinforcement Learning on SMAC corridor (medium-poor)Follow9.7Average ScoreOMIGA6.03926.98967.948.8904Jul 21, 2023Evaluation resultsMethodMethodLinksAverage ScoreOMIGArandom seeds=5random seeds=52023.079.7ICQrandom seeds=5random seeds=52023.078.27BCQ-MArandom seeds=5random seeds=52023.078.11OMARrandom seeds=5random seeds=52023.076.25CQL-MArandom seeds=5random seeds=52023.076.18