ResearchBenchmarksOffline Reinforcement Learning on Hopper (Hp) Medium-Replay 1TOffline Reinforcement Learning on Hopper (Hp) Medium-Replay 1TFollow83.406Normalized ScoreQT2.1383223.2366644.33565.43334Oct 30, 2024Evaluation resultsMethodMethodLinksNormalized ScoreQTSource Dataset=1TSource Dataset=1T2024.1083.406CQLSource Dataset=1TSource Dataset=1T2024.1071.401BCQSource Dataset=1TSource Dataset=1T2024.1068.448DTSource Dataset=1TSource Dataset=1T2024.1061.686AWRSource Dataset=1TSource Dataset=1T2024.1054.259ReinformerSource Dataset=1TSource Dataset=1T2024.1036.008MOPOSource Dataset=1TSource Dataset=1T2024.105.849BEARSource Dataset=1TSource Dataset=1T2024.105.264