ResearchBenchmarksOffline Reinforcement Learning on D4RL POMDP HalfCheetah (Medium-Expert)Follow94.9Normalized ScoreTT16.036836.510956.98577.4591Jun 9, 2023Evaluation ResultsMethodMethodLinksNormalized ScoreTT2023.0694.9Decision Stacks2023.0692.7Diffuser2023.0682.2DT2023.0680.8BC2023.0642.1DD2023.0619.07