ResearchTasksAverage-reward Regret MinimizationAverage-reward Regret MinimizationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAverage-reward MDPsCorollary 3.6 (FOCUS)1Regret Bound1Mar 26, 2026