A note on structural properties of the Bernoulli two-armed bandit problem

DOI10.1080/02331938208842808zbMATH Open0505.90080OpenAlexW2014864288MaRDI QIDQ4742584FDOQ4742584

Authors: Radu Theodorescu, Dieter Kalin 

Publication date: 1982

Published in: Mathematische Operationsforschung und Statistik. Series Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/02331938208842808

zbMATH Keywords

monotonicity propertyfinite horizonBernoulli two-armed bandit problemoptimal expected cumulative discounted reward

Mathematics Subject Classification ID

Dynamic programming (90C39)

Cited In (3)

• A Two-Armed Bandit Problem with possibility of no Information
• On the Bernoulli three-armed bandit problem
• On monotone optimal decision rules and the stay-on-a-winner rule for the two-armed bandit

This page was built for publication: A note on structural properties of the Bernoulli two-armed bandit problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4742584)