ResearchTasksPerformative Reinforcement LearningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedExponential family PeMDPsPePG0Regulariser Lambda1Feb 26, 2026Direct PeMDPs——Primary metric0Feb 26, 2026