ResearchTasksExpected rewards maximization under optimal transport distance regularizationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedIllustrative Synthetic Environment v1 (test)FDC-A35.4Expected Reward E[r(x)]3Feb 26, 2026