ResearchTasksOffline Reinforcement Learning Policy EvaluationOffline Reinforcement Learning Policy EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMIMIC-III and MIMIC-IV (offline)T-CQL0.87FQE Score4Mar 13, 2026