ResearchBenchmarksOffline Reinforcement Learning on Walker2D Medium-Replay 1TFollow67.546Normalized ScoreQT-1.8937616.1338734.161552.18913Oct 30, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreQTSource Dataset=1TSource Dataset=1T2024.1067.546BCQSource Dataset=1TSource Dataset=1T2024.1060.638CQLSource Dataset=1TSource Dataset=1T2024.1057.402ReinformerSource Dataset=1TSource Dataset=1T2024.1038.072DTSource Dataset=1TSource Dataset=1T2024.1034.482AWRSource Dataset=1TSource Dataset=1T2024.1028.426MOPOSource Dataset=1TSource Dataset=1T2024.1020.313BEARSource Dataset=1TSource Dataset=1T2024.100.777