ResearchDatasetsSkew-t reward distributionSkew-t reward distributionFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMulti-armed bandit policy evaluationSkew-t reward distribution Δ = 0.05 1,000 MC replicates synthetic91.49Coverage (Arm1)6
Multi-armed bandit policy evaluationSkew-t reward distribution Δ = 0.05 1,000 MC replicates synthetic91.49Coverage (Arm1)6