We study the structure of regret-minimizing policies in the many-armed Bayesian multi-armed bandit problem: in particular, with k the number of arms and T the time horizon, we consider the case where k > sqrt{T}. We first show that subsampling is a critical step for designing optimal policies. In particular, the standard UCB algorithm leads to sub-optimal regret bounds in this regime. However, a subsampled UCB (SS-UCB), which samples sqrt{T} arms and executes UCB only on that subset, is rate-optimal. Despite theoretically optimal regret, even SS-UCB performs poorly due to excessive exploration of suboptimal arms. In fact, in numerical experiments SS-UCB performs worse than a simple greedy algorithm (and its subsampled version) that pulls the current empirical best arm at every time period. We show that these insights hold even in a contextual setting, using real-world data. These empirical results suggest a novel form of free exploration in the many-armed regime that benefits greedy algorithms. We theoretically study this new source of free exploration and find that it is deeply connected to the distribution of a certain tail event for the prior distribution of arm rewards. This is a fundamentally distinct phenomenon from free exploration as discussed in the recent literature on contextual bandits, where free exploration arises due to variation in contexts. We prove that the subsampled greedy algorithm is rate-optimal for Bernoulli bandits when k > sqrt{T}, and achieves sublinear regret with more general distributions. This is a case where theoretical rate optimality does not tell the whole story: when complemented by the empirical observations of our paper, the power of greedy algorithms becomes quite evident. Taken together, from a practical standpoint, our results suggest that in applications it may be preferable to use a variant of the greedy algorithm in the many-armed regime.
Download