ResearchTasksAction-Value coverage estimationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedRiverSwim mostly-right target policy T=50Model-based bootstrap with percentile CI0.523Q-Value Estimate (s=1, a=0)20May 13, 2026RiverSwim T=100Model-based bootstrap0.907Q*(1,0)15May 13, 2026
RiverSwim mostly-right target policy T=50Model-based bootstrap with percentile CI0.523Q-Value Estimate (s=1, a=0)20May 13, 2026