ResearchDatasetsWeakly communicating average-reward MDPsWeakly communicating average-reward MDPsFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsFinding an ε-optimal policy from a single trajectoryWeakly communicating average-reward MDPs-2Sample Complexity (Exponent on ε)2
Finding an ε-optimal policy from a single trajectoryWeakly communicating average-reward MDPs-2Sample Complexity (Exponent on ε)2