ResearchBenchmarksOffline Reinforcement Learning on HalfCheetah (Hc) Medium-Replay 10TFollow59.724Normalized ScoreMOPO17.9825628.8192839.65650.49272Oct 30, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreMOPOSource Dataset=10TSource Dataset=10T2024.1059.724QTSource Dataset=10TSource Dataset=10T2024.1049.587CQLSource Dataset=10TSource Dataset=10T2024.1046.966AWRSource Dataset=10TSource Dataset=10T2024.1041.041ReinformerSource Dataset=10TSource Dataset=10T2024.1039.434BCQSource Dataset=10TSource Dataset=10T2024.1038.575DTSource Dataset=10TSource Dataset=10T2024.1034.508BEARSource Dataset=10TSource Dataset=10T2024.1019.588