ResearchDatasetsErgodic average-reward MDPsErgodic average-reward MDPsFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsFinding an ε-optimal policy from a single trajectoryErgodic average-reward MDPs-2Sample Complexity Exponent (vs ε)1
Finding an ε-optimal policy from a single trajectoryErgodic average-reward MDPs-2Sample Complexity Exponent (vs ε)1