Average optimality in a Poissonian bandit with switching arms

DOI10.1007/BF01193865zbMath0882.90126OpenAlexW2071619734MaRDI QIDQ1362683

Alexander A. Yushkevich, Doncho S. Donchev

Publication date: 5 August 1997

Published in: Mathematical Methods of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf01193865

zbMATH Keywords

continuous timeswitching armsaverage criterionsymmetric Poissonian two-armed bandit

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Sequential statistical design (62L05) Probabilistic games; gambling (91A60)

Related Items (1)

On the two-armed bandit problem with non-observed Poissonian switching of arms.

Cites Work

• Unnamed Item
• Poisson Version of the Two-Armed Bandit Problem with Discounting
• Verification Theorems for Markov Decision Processes with Controlled Deterministic Drift and Gradual and Impulsive Controls
• Optimal control of piecewise deterministic markov process
• On the two-armed bandit problem with continuous time parameter and discounted rewards
• Contributions to the "Two-Armed Bandit" Problem

This page was built for publication: Average optimality in a Poissonian bandit with switching arms