?-best-arm identification in pay-per-reward multi-armed bandits

Sivan Sabato

?-best-arm identification in pay-per-reward multi-armed bandits

Sivan Sabato

Department of Computer Science

Research output: Contribution to journal › Conference article › peer-review

3 Scopus citations

Abstract

We study ?-best-arm identification, in a setting where during the exploration phase, the cost of each arm pull is proportional to the expected future reward of that arm. We term this setting Pay-Per-Reward. We provide an algorithm for this setting, that with a high probability returns an ?-best arm, while incurring a cost that depends only linearly on the total expected reward of all arms, and does not depend at all on the number of arms. Under mild assumptions, the algorithm can be applied also to problems with infinitely many arms.

Original language	English
Journal	Advances in Neural Information Processing Systems
Volume	32
State	Published - 1 Jan 2019
Event	33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019 - Vancouver, Canada Duration: 8 Dec 2019 → 14 Dec 2019

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

@article{0a6683b51b9945b0840ad7a349f7e747,

title = "?-best-arm identification in pay-per-reward multi-armed bandits",

abstract = "We study ?-best-arm identification, in a setting where during the exploration phase, the cost of each arm pull is proportional to the expected future reward of that arm. We term this setting Pay-Per-Reward. We provide an algorithm for this setting, that with a high probability returns an ?-best arm, while incurring a cost that depends only linearly on the total expected reward of all arms, and does not depend at all on the number of arms. Under mild assumptions, the algorithm can be applied also to problems with infinitely many arms.",

author = "Sivan Sabato",

note = "Publisher Copyright: {\textcopyright} 2019 Neural information processing systems foundation. All rights reserved.; 33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019 ; Conference date: 08-12-2019 Through 14-12-2019",

year = "2019",

month = jan,

day = "1",

language = "English",

volume = "32",

journal = "Advances in Neural Information Processing Systems",

issn = "1049-5258",

publisher = "Neural information processing systems foundation",

}

TY - JOUR

T1 - ?-best-arm identification in pay-per-reward multi-armed bandits

AU - Sabato, Sivan

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We study ?-best-arm identification, in a setting where during the exploration phase, the cost of each arm pull is proportional to the expected future reward of that arm. We term this setting Pay-Per-Reward. We provide an algorithm for this setting, that with a high probability returns an ?-best arm, while incurring a cost that depends only linearly on the total expected reward of all arms, and does not depend at all on the number of arms. Under mild assumptions, the algorithm can be applied also to problems with infinitely many arms.

AB - We study ?-best-arm identification, in a setting where during the exploration phase, the cost of each arm pull is proportional to the expected future reward of that arm. We term this setting Pay-Per-Reward. We provide an algorithm for this setting, that with a high probability returns an ?-best arm, while incurring a cost that depends only linearly on the total expected reward of all arms, and does not depend at all on the number of arms. Under mild assumptions, the algorithm can be applied also to problems with infinitely many arms.

UR - http://www.scopus.com/inward/record.url?scp=85090177746&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85090177746

SN - 1049-5258

VL - 32

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

T2 - 33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019

Y2 - 8 December 2019 through 14 December 2019

ER -

?-best-arm identification in pay-per-reward multi-armed bandits

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this