ResearchTasksReward MaximizationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSHPAISP0.53Win Rate12Feb 26, 2026Illustrative Setting Novelty-seeking reward maximizationFDC452.5SQ_beta4Feb 26, 2026