ResearchBenchmarksOffline Reinforcement Learning on D4RL Hopper (Simultaneous Random Corruption)Offline Reinforcement Learning on D4RL Hopper (Simultaneous Random Corruption)Follow28.83Average ScoreTRACER-0.32127.246914.81522.3831Nov 1, 2024Evaluation resultsMethodMethodLinksAverage ScoreTRACER2024.1128.83IQL2024.1125.28RIQL2024.1122.5BC2024.1118.49MSG2024.1115.84UWMSG2024.1112.22CQL2024.113.16EDAC2024.110.8