Optimal activation of halting multi-armed bandit models

Wesley Cowan; Michael N. Katehakis; Sheldon M. Ross

doi:10.1002/nav.22145

Optimal activation of halting multi-armed bandit models

Wesley Cowan, Michael N. Katehakis, Sheldon M. Ross

Rutgers Business School, Management & Information Systems

Research output: Contribution to journal › Article › peer-review

Abstract

We study new types of dynamic allocation problems the Halting Bandit models. As an application, we obtain new proofs for the classic Gittins index decomposition result compare Gittins (Journal of the Royal Statistical Society, Series B, 1979, 41, 148–177), and recent results of the authors in Cowan and Katehakis (Probability in the Engineering and Informational Sciences, 2015, 29, 51–76).

Original language	English (US)
Pages (from-to)	639-652
Number of pages	14
Journal	Naval Research Logistics
Volume	70
Issue number	7
DOIs	https://doi.org/10.1002/nav.22145
State	Published - Oct 2023

All Science Journal Classification (ASJC) codes

Modeling and Simulation
Ocean Engineering
Management Science and Operations Research

Keywords

Markovian decision processes
adaptive systems
autonomous reasoning and learning
dynamic data driven systems
machine learning

Access to Document

10.1002/nav.22145

Cite this

@article{84aa35232aad4766832978c8bd072351,

title = "Optimal activation of halting multi-armed bandit models",

abstract = "We study new types of dynamic allocation problems the Halting Bandit models. As an application, we obtain new proofs for the classic Gittins index decomposition result compare Gittins (Journal of the Royal Statistical Society, Series B, 1979, 41, 148–177), and recent results of the authors in Cowan and Katehakis (Probability in the Engineering and Informational Sciences, 2015, 29, 51–76).",

keywords = "Markovian decision processes, adaptive systems, autonomous reasoning and learning, dynamic data driven systems, machine learning",

author = "Wesley Cowan and Katehakis, {Michael N.} and Ross, {Sheldon M.}",

note = "Publisher Copyright: {\textcopyright} 2023 The Authors. Naval Research Logistics published by Wiley Periodicals LLC.",

year = "2023",

month = oct,

doi = "10.1002/nav.22145",

language = "English (US)",

volume = "70",

pages = "639--652",

journal = "Naval Research Logistics",

issn = "0894-069X",

publisher = "John Wiley and Sons Inc.",

number = "7",

}

TY - JOUR

T1 - Optimal activation of halting multi-armed bandit models

AU - Cowan, Wesley

AU - Katehakis, Michael N.

AU - Ross, Sheldon M.

PY - 2023/10

Y1 - 2023/10

N2 - We study new types of dynamic allocation problems the Halting Bandit models. As an application, we obtain new proofs for the classic Gittins index decomposition result compare Gittins (Journal of the Royal Statistical Society, Series B, 1979, 41, 148–177), and recent results of the authors in Cowan and Katehakis (Probability in the Engineering and Informational Sciences, 2015, 29, 51–76).

AB - We study new types of dynamic allocation problems the Halting Bandit models. As an application, we obtain new proofs for the classic Gittins index decomposition result compare Gittins (Journal of the Royal Statistical Society, Series B, 1979, 41, 148–177), and recent results of the authors in Cowan and Katehakis (Probability in the Engineering and Informational Sciences, 2015, 29, 51–76).

KW - Markovian decision processes

KW - adaptive systems

KW - autonomous reasoning and learning

KW - dynamic data driven systems

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=85168326322&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85168326322&partnerID=8YFLogxK

U2 - 10.1002/nav.22145

DO - 10.1002/nav.22145

M3 - Article

AN - SCOPUS:85168326322

SN - 0894-069X

VL - 70

SP - 639

EP - 652

JO - Naval Research Logistics

JF - Naval Research Logistics

IS - 7

ER -

Optimal activation of halting multi-armed bandit models

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this