ResearchBenchmarksOffline Reinforcement Learning on Walker2D (W2D) 10T MediumFollow88.262Normalized ScoreQT10.1382430.4203750.702570.98463Oct 30, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreQTSource Dataset=10TSource Dataset=10T2024.1088.262ReinformerSource Dataset=10TSource Dataset=10T2024.1081.377DTSource Dataset=10TSource Dataset=10T2024.1079.697CQLSource Dataset=10TSource Dataset=10T2024.1078.191AWRSource Dataset=10TSource Dataset=10T2024.1078.06BCQSource Dataset=10TSource Dataset=10T2024.1074.735MOPOSource Dataset=10TSource Dataset=10T2024.1022.261BEARSource Dataset=10TSource Dataset=10T2024.1013.143