paper

Optimally Confident UCB: Improved Regret for Finite-Armed Bandits

arXiv:1507.07880

Abstract

I present the first algorithm for stochastic finite-armed bandits that simultaneously enjoys order-optimal problem-dependent regret and worst-case regret. Besides the theoretical results, the new algorithm is simple, efficient and empirically superb. The approach is based on UCB, but with a carefully chosen confidence parameter that optimally balances the risk of failing confidence intervals against the cost of excessive optimism.

arXiv comment26 pages

References in corpus (8)

Cited by in corpus (9)