ResearchBenchmarksOffline Reinforcement Learning on D4RL Walker2d Simultaneous Adversarial CorruptionFollow17.21Avg ScoreTRACER-0.86523.82748.5213.2126Nov 1, 2024Evaluation ResultsMethodMethodLinksAvg ScoreTRACER2024.1117.21IQL2024.1116.61RIQL2024.119.2BC2024.116.75CQL2024.114.23UWMSG2024.114.19MSG2024.113.77EDAC2024.11-0.17