ResearchBenchmarksOffline Reinforcement Learning on D4RL POMDP HalfCheetah Medium-ReplayFollow43.8Normalized ScoreTT0.43211.69122.9534.209Jun 9, 2023Evaluation ResultsMethodMethodLinksNormalized ScoreTT2023.0643.8Decision Stacks2023.0640.3DD2023.0639.8Diffuser2023.0639.3DT2023.0635.5BC2023.062.1