ResearchBenchmarksOffline Reinforcement Learning on Walker2D (W2D) 10T Medium-ExpertFollow111.394Normalized ScoreQT17.5880841.9415466.29590.64846Oct 30, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreQTSource Dataset=10TSource Dataset=10T2024.10111.394ReinformerSource Dataset=10TSource Dataset=10T2024.10109.845AWRSource Dataset=10TSource Dataset=10T2024.10109.154DTSource Dataset=10TSource Dataset=10T2024.10108.622BCQSource Dataset=10TSource Dataset=10T2024.10101.84CQLSource Dataset=10TSource Dataset=10T2024.10101.84BEARSource Dataset=10TSource Dataset=10T2024.1021.383MOPOSource Dataset=10TSource Dataset=10T2024.1021.196