ResearchTasksOptimal Policy SelectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedStochastic Gridworld (S=16, A=4)LazyGradient100PCS28May 28, 2026International Stroke Trial (IST) empirical (sample (N = 19,435))T-a-S-CS73.7PCS15May 12, 2026Symmetric MNE Contest ModelStructured Optimal Policy1Optimal Policy Selection2Apr 7, 2026