Optimal activation of halting multi-armed bandit models

Research output: Contribution to journalArticlepeer-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 languageEnglish (US)
Pages (from-to)639-652
Number of pages14
JournalNaval Research Logistics
Volume70
Issue number7
DOIs
StatePublished - Oct 2023

ASJC Scopus subject areas

  • 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

Fingerprint

Dive into the research topics of 'Optimal activation of halting multi-armed bandit models'. Together they form a unique fingerprint.

Cite this