ResearchTasksOffline Policy OptimizationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedD4RL v2PhyB33.9Hopper Score (Random)5Jun 2, 2026MIMIC-III Sepsis (test)P4L-5.4Performance Value5Mar 10, 2026