An efficient bandit algorithm for general weight assignments

In this paper, we study the adversarial multi armed bandit problem and present a generally implementable efficient bandit arm selection structure. Since we do not have any statistical assumptions on the bandit arm losses, the results in the paper are guaranteed to hold in an individual sequence mann...

Full description

Saved in:
Bibliographic Details
Published in2017 25th Signal Processing and Communications Applications Conference (SIU) pp. 1 - 4
Main Authors Gokcesu, Kaan, Ergen, Tolga, Ciftci, Selami, Kozat, Suleyman S.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2017
Subjects
adversarial multi-armed bandit
Dogs
efficient implementation
general framework
Switches
switching bandit
Table lookup
Online AccessGet full text

Cover

More Information
Summary:In this paper, we study the adversarial multi armed bandit problem and present a generally implementable efficient bandit arm selection structure. Since we do not have any statistical assumptions on the bandit arm losses, the results in the paper are guaranteed to hold in an individual sequence manner. The introduced framework is able to achieve the optimal regret bounds by employing general weight assignments on bandit arm selection sequences. Hence, this framework can be used for a wide range of applications.
DOI:10.1109/SIU.2017.7960214