ResearchDatasetsSkew-t reward scenarioSkew-t reward scenarioFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsBandit Interval Coverage and Width EvaluationSkew-t reward scenario Delta = 0.5 synthetic (1,000 MC replicates)80.3Coverage Arm16
Bandit Interval Coverage and Width EvaluationSkew-t reward scenario Delta = 0.5 synthetic (1,000 MC replicates)80.3Coverage Arm16