ResearchDatasetsStair arm-to-reward functionStair arm-to-reward functionFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsBest Arm IdentificationStair arm-to-reward function K=550.57Error Rate15Best Arm IdentificationStair arm-to-reward function K=210.09Error Probability15Best Arm IdentificationStair arm-to-reward function K=150.02Error Rate15