ResearchBenchmarksOffline Reinforcement Learning on Hopper (Hp) 10T MediumFollow90.176Normalized ScoreQT17.6068836.4469455.28774.12706Oct 30, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreQTSource Dataset=10TSource Dataset=10T2024.1090.176DTSource Dataset=10TSource Dataset=10T2024.1085.589CQLSource Dataset=10TSource Dataset=10T2024.1082.945ReinformerSource Dataset=10TSource Dataset=10T2024.1077.792BCQSource Dataset=10TSource Dataset=10T2024.1073.462AWRSource Dataset=10TSource Dataset=10T2024.1064.494MOPOSource Dataset=10TSource Dataset=10T2024.1032.769BEARSource Dataset=10TSource Dataset=10T2024.1020.398