List your company

Best Arm Identification on Synthetic Multi-Armed Bandit (N=1,024, T=10,240) T = N log2 N (test)

0.0195Avg Simple RegretSH
0.0100480.0738490.137650.201451Feb 20, 2026

Evaluation results

MethodLinks
SHKnowledge of T=Yes (Fixed), r0=1.72026.020.019500.029
B3Knowledge of T=No (Anytime)2026.020.026800.0502
SHKnowledge of T=Yes (Fixed), r0=2.02026.020.028800.0507
UCB-EKnowledge of T=Yes (Fixed)2026.020.04030.02220.0588
BSHKnowledge of T=No (Anytime)2026.020.15310.06610.2475
BUCBKnowledge of T=No (Anytime)2026.020.25580.23740.3039