ResearchDatasetsDR19FollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsOffline Reinforcement LearningDR19 150-5-mid57NAUC4Reinforcement Learning target performance estimationDR19 150-5-late0.4NAUC4Offline In-Context Reinforcement LearningDR19-150-5 (complete)64NAUC4Offline In-Context Reinforcement LearningDR19-300-5-early (test)56NAUC4