ResearchBenchmarksOffline Reinforcement Learning on Walker2D (W2D) Medium-Expert 1TFollow111.722Normalized ScoreQT5.168832.8316560.494588.15735Oct 30, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreQTSource Dataset=1TSource Dataset=1T2024.10111.722DTSource Dataset=1TSource Dataset=1T2024.10107.171ReinformerSource Dataset=1TSource Dataset=1T2024.10103.284CQLSource Dataset=1TSource Dataset=1T2024.10101.611BCQSource Dataset=1TSource Dataset=1T2024.10101.61AWRSource Dataset=1TSource Dataset=1T2024.10100.566MOPOSource Dataset=1TSource Dataset=1T2024.1020.569BEARSource Dataset=1TSource Dataset=1T2024.109.267