ResearchDatasetsDR9DR9FollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsReinforcement Learning target performance estimationDR9 70-5-late63NAUC4Reinforcement Learning target performance estimationDR9 40-1-late33NAUC4Reinforcement Learning target performance estimationDR9 20-1-late15NAUC4Offline In-Context Reinforcement LearningDR9 70-5-early (test)50NAUC4Offline In-Context Reinforcement LearningDR9-40-1-early (test)21NAUC4