Pith. sign in

Optimally Confident UCB: Improved Regret for Finite-Armed Bandits

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
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.

fields

cs.IR 1

years

2019 1

verdicts

CONDITIONAL 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.