On the Optimal Sample Complexity for Best Arm Identification

Abstract

We study the best arm identification (BEST-1-ARM) problem, which is defined as follows. We are given $n$ stochastic bandit arms. The $i$th arm has a reward distribution $D_i$ with an unknown mean ${\mu }_i$. Upon each play of the $i$th arm, we can get a reward, sampled i.i.d. from $D_i$. We would like to identify the arm with the largest mean with probability at least $1-\delta$, using as few samples as possible. We provide a nontrivial algorithm for BEST-1-ARM, which improves upon several prior upper bounds on the same problem. We also study an important special case where there are only two arms, which we call the sign problem. We provide a new lower bound of sign, simplifying and significantly extending a classical result by Farrell in 1964, with a completely new proof. Using the new lower bound for sign, we obtain the first lower bound for BEST-1-ARM that goes beyond the classic Mannor-Tsitsiklis lower bound, by an interesting reduction from Sign to BEST-1-ARM. We propose an interesting conjecture concerning the optimal sample complexity of BEST-1-ARM from the perspective of instance-wise optimality.

Cited by in corpus (7)

• An optimal algorithm for the Thresholding Bandit Problem
• Towards Instance Optimal Bounds for Best Arm Identification
• Polynomial-time Algorithms for Multiple-arm Identification with Full-bandit Feedback
• Pure Exploration of Multi-armed Bandit Under Matroid Constraints
• Playing against Nature: causal discovery for decision making under uncertainty
• Best Arm Identification for Contaminated Bandits
• Open Problem: Best Arm Identification: Almost Instance-Wise Optimality and the Gap Entropy Conjecture