ResearchBenchmarksOffline Reinforcement Learning on Walker2D (W2D) Medium 1TFollow81.756Normalized ScoreQT1.5532822.3751443.19764.01886Oct 30, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreQTSource Dataset=1TSource Dataset=1T2024.1081.756ReinformerSource Dataset=1TSource Dataset=1T2024.1079.034AWRSource Dataset=1TSource Dataset=1T2024.1068.023DTSource Dataset=1TSource Dataset=1T2024.1067.261CQLSource Dataset=1TSource Dataset=1T2024.1065.618BCQSource Dataset=1TSource Dataset=1T2024.1062.567MOPOSource Dataset=1TSource Dataset=1T2024.1020.953BEARSource Dataset=1TSource Dataset=1T2024.104.638