ResearchDatasetsD4RL MuJoCo HalfcheetahFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsOffline Reinforcement LearningD4RL MuJoCo Halfcheetah medexp standard108.2Normalized Score8