ResearchBenchmarksOffline Reinforcement Learning on HalfCheetah 1T Medium-ReplayFollow32.318Normalized ScoreQT0.373368.6666816.9625.25332Oct 30, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreQTSource Dataset=1TSource Dataset=1T2024.1032.318AWRSource Dataset=1TSource Dataset=1T2024.1028.023CQLSource Dataset=1TSource Dataset=1T2024.1026.955BCQSource Dataset=1TSource Dataset=1T2024.1025.828ReinformerSource Dataset=1TSource Dataset=1T2024.1018.493DTSource Dataset=1TSource Dataset=1T2024.1015.164MOPOSource Dataset=1TSource Dataset=1T2024.1012.277BEARSource Dataset=1TSource Dataset=1T2024.101.602