ResearchBenchmarksOffline Multi-Agent Reinforcement Learning on SMAC corridor (good-medium)Offline Multi-Agent Reinforcement Learning on SMAC corridor (good-medium)Follow14.02Average ScoreOMIGA5.447.66759.89512.1225Jul 21, 2023Evaluation resultsMethodMethodLinksAverage ScoreOMIGArandom seeds=5random seeds=52023.0714.02BCQ-MArandom seeds=5random seeds=52023.0713.32ICQrandom seeds=5random seeds=52023.0712.98OMARrandom seeds=5random seeds=52023.076.63CQL-MArandom seeds=5random seeds=52023.075.77