ResearchBenchmarksOffline Multi-agent Reinforcement Learning on Warehouse Small (11x20)Follow5.97Mean Performance (N=2)AlberDICE3.55724.18364.815.4364Nov 3, 2023Evaluation ResultsMethodMethodLinksMean Performance (N=2)Mean Performance (N=4)Mean Performance (N=6)AlberDICE2023.115.978.189.65BC2023.115.547.888.9ICQ2023.115.437.938.87OptiDICE2023.114.847.688.47OMAR2023.114.47.128.41MADTKD2023.113.656.857.85