ResearchBenchmarksOffline Reinforcement Learning on D4RL POMDP Walker2d Medium-ReplayFollow66.8Normalized ScoreDecision Stacks7.93623.21838.553.782Jun 9, 2023Evaluation ResultsMethodMethodLinksNormalized ScoreDecision Stacks2023.0666.8Diffuser2023.0658.7DD2023.0658.4DT2023.0645.3BC2023.0623.8TT2023.0610.2