IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Online ISSN : 1745-1337
Print ISSN : 0916-8508
Regular Section
UCB-SC: A Fast Variant of KL-UCB-SC for Budgeted Multi-Armed Bandit Problem
Ryo WATANABEJunpei KOMIYAMAAtsuyoshi NAKAMURAMineichi KUDO
Author information
JOURNALS RESTRICTED ACCESS

2018 Volume E101.A Issue 3 Pages 662-667

Details
Abstract

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.

Information related to the author
© 2018 The Institute of Electronics, Information and Communication Engineers
Previous article
feedback
Top