Exploring k out of Top ρ Fraction of Arms in Stochastic Bandits

This paper studies the problem of identifying any k distinct arms among the top ρ fraction (e.g., top 5%) of arms from a finite or infinite set with a probably approximately correct (PAC) tolerance ε. We consider two cases: (i) when the threshold of the top arms' expected rewards is known and (ii) when it is unknown. We prove lower bounds for the four variants (finite or infinite arms, and known or unknown threshold), and propose algorithms for each. Two of these algorithms are shown to be sample complexity optimal (up to constant factors) and the other two are optimal up to a log factor. Results in this paper provide up to ρ n/k reductions compared with the "k-exploration" algorithms that focus on finding the (PAC) best k arms out of n arms. We also numerically show improvements over the state-of-the-art.