ResearchBenchmarksOffline Reinforcement Learning on D4RL Antmaze-umaze-diverse 1M (full)Follow71.4Normalized ScoreTD3+BC42.2849.8457.464.96Jun 7, 2023Evaluation ResultsMethodMethodLinksNormalized ScoreTD3+BCRatio=1, Size=1MRatio=1, Size=1M2023.0671.4IQLRatio=1, Size=1MRatio=1, Size=1M2023.0666.7BCRatio=1, Size=1MRatio=1, Size=1M2023.0645.6CQLRatio=1, Size=1MRatio=1, Size=1M2023.0643.4