ResearchDatasetsStudent-t reward distributionStudent-t reward distributionFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMulti-armed bandit policy evaluationStudent-t reward distribution Δ = 0.05 synthetic (1,000 MC replicates)81.29Coverage (Arm1)6
Multi-armed bandit policy evaluationStudent-t reward distribution Δ = 0.05 synthetic (1,000 MC replicates)81.29Coverage (Arm1)6