ResearchBenchmarksOffline Reinforcement Learning on HalfCheetah (Hc) 1T MediumFollow64.329Normalized ScoreMOPO0.192216.843133.49450.1449Oct 30, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreMOPOSource Dataset=1TSource Dataset=1T2024.1064.329QTSource Dataset=1TSource Dataset=1T2024.1050.464CQLSource Dataset=1TSource Dataset=1T2024.1044.393ReinformerSource Dataset=1TSource Dataset=1T2024.1042.958AWRSource Dataset=1TSource Dataset=1T2024.1041.672DTSource Dataset=1TSource Dataset=1T2024.1041.204BCQSource Dataset=1TSource Dataset=1T2024.1041.051BEARSource Dataset=1TSource Dataset=1T2024.102.659