ResearchBenchmarksOffline Reinforcement Learning on Hopper 10T Medium-ReplayFollow100.321Normalized ScoreQT1.7633227.3504152.937578.52459Oct 30, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreQTSource Dataset=10TSource Dataset=10T2024.10100.321CQLSource Dataset=10TSource Dataset=10T2024.1073.168DTSource Dataset=10TSource Dataset=10T2024.1069.701BCQSource Dataset=10TSource Dataset=10T2024.1060.385AWRSource Dataset=10TSource Dataset=10T2024.1057.548ReinformerSource Dataset=10TSource Dataset=10T2024.1039.856MOPOSource Dataset=10TSource Dataset=10T2024.108.638BEARSource Dataset=10TSource Dataset=10T2024.105.554