ResearchBenchmarksOffline Reinforcement Learning on Hopper (Hp) 1T MediumFollow74.737Normalized ScoreReinformer6.1313223.9424141.753559.56459Oct 30, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreReinformerSource Dataset=1TSource Dataset=1T2024.1074.737CQLSource Dataset=1TSource Dataset=1T2024.1074.489QTSource Dataset=1TSource Dataset=1T2024.1070.927DTSource Dataset=1TSource Dataset=1T2024.1066.073BCQSource Dataset=1TSource Dataset=1T2024.1063.308AWRSource Dataset=1TSource Dataset=1T2024.1055.269MOPOSource Dataset=1TSource Dataset=1T2024.1031.038BEARSource Dataset=1TSource Dataset=1T2024.108.77