ResearchBenchmarksOffline Reinforcement Learning on Hopper (Hp) 1T Medium-ExpertFollow108.225Normalized ScoreQT28.9177249.5071170.096590.68589Oct 30, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreQTSource Dataset=1TSource Dataset=1T2024.10108.225DTSource Dataset=1TSource Dataset=1T2024.10100.719CQLSource Dataset=1TSource Dataset=1T2024.1082.071BCQSource Dataset=1TSource Dataset=1T2024.1062.287ReinformerSource Dataset=1TSource Dataset=1T2024.1060.753AWRSource Dataset=1TSource Dataset=1T2024.1054.098MOPOSource Dataset=1TSource Dataset=1T2024.1035.099BEARSource Dataset=1TSource Dataset=1T2024.1031.968