List your company

Best Arm Identification on Synthetic Bandit (N=128, T=896)

0.0446Average Simple RegretSH (r0 = 1.7)
0.0413760.0631380.08490.106662Feb 20, 2026

Evaluation results

MethodLinks
SH (r0 = 1.7)Knowledge of T=Yes (Fixed)2026.020.04460.02810.0652
B3Knowledge of T=No (Anytime)2026.020.0490.0290.0682
SH (r0 = 2.0)Knowledge of T=Yes (Fixed)2026.020.05160.0290.0682
UCB-EKnowledge of T=Yes (Fixed)2026.020.06640.05020.0749
BSHKnowledge of T=No (Anytime)2026.020.09920.05870.1569
BUCBKnowledge of T=No (Anytime)2026.020.12520.06820.1769