ResearchBenchmarksOffline Reinforcement Learning on Hopper (Hp) 10T Medium-ExpertFollow112.908Normalized ScoreQT33.0911253.8128174.534595.25619Oct 30, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreQTSource Dataset=10TSource Dataset=10T2024.10112.908DTSource Dataset=10TSource Dataset=10T2024.10108.087AWRSource Dataset=10TSource Dataset=10T2024.10105.361BCQSource Dataset=10TSource Dataset=10T2024.10102.775CQLSource Dataset=10TSource Dataset=10T2024.10102.071BEARSource Dataset=10TSource Dataset=10T2024.1088.236ReinformerSource Dataset=10TSource Dataset=10T2024.1079.389MOPOSource Dataset=10TSource Dataset=10T2024.1036.161