On the Optimal Sample Complexity for Best Arm Identification

We study the best arm identification (BEST-1-ARM) problem, which is defined as follows. We are given n stochastic bandit arms. The ith arm has a reward distribution Di with an unknown mean μi. Upon each play of the ith arm, we can get a reward, sampled i.i.d. from Di. We would like to identify the arm with the largest mean with probability at least 1-δ, 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.