ResearchBenchmarksOffline Reinforcement Learning on Walker2D Medium-Replay 10TFollow85.092Normalized ScoreQT2.682424.077245.47266.8668Oct 30, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreQTSource Dataset=10TSource Dataset=10T2024.1085.092CQLSource Dataset=10TSource Dataset=10T2024.1080.145DTSource Dataset=10TSource Dataset=10T2024.1068.528ReinformerSource Dataset=10TSource Dataset=10T2024.1068.168BCQSource Dataset=10TSource Dataset=10T2024.1064.735AWRSource Dataset=10TSource Dataset=10T2024.1058.286MOPOSource Dataset=10TSource Dataset=10T2024.1018.529BEARSource Dataset=10TSource Dataset=10T2024.105.852