ResearchTasksModel-free learningModel-free learningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedStochastic MDPs Bilinear or BEDu et al. (2021), Jin et al. (2021), Xie et al. (2023)2Regret T Exponent6Mar 20, 2026Toy 3-arm MDPDig-DEC1Regret (T-dependence)1Mar 20, 2026
Stochastic MDPs Bilinear or BEDu et al. (2021), Jin et al. (2021), Xie et al. (2023)2Regret T Exponent6Mar 20, 2026