For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
UCB-SC: A Fast Variant of KL-UCB-SC for Budgeted Multi-Armed Bandit Problem
Ryo WATANABE Junpei KOMIYAMA Atsuyoshi NAKAMURA Mineichi KUDO
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2018/03/01
Online ISSN: 1745-1337
Type of Manuscript: LETTER
Category: Mathematical Systems Science
budgeted multi-armed bandits, regret analysis, upper confidence bound,
Full Text: PDF(967.8KB)>>
We propose a policy UCB-SC for budgeted multi-armed bandits. The policy is a variant of recently proposed KL-UCB-SC. Unlike KL-UCB-SC, which is computationally prohibitive, UCB-SC runs very fast while keeping KL-UCB-SC's asymptotical optimality when reward and cost distributions are Bernoulli with means around 0.5, which are verified both theoretically and empirically.