Bandit bounds from stochastic variability extrema

DOI10.1016/S0167-7152(97)00024-2MaRDI QIDQ1373975zbMATH OpenFDO

Authors Stephen J. Herschkorn

Publication date 26 November 1997

Published in Statistics \& Probability Letters (Search for Journal in Brave)

zbMATH Keywords

bandit problemsvalue of informationconvex orderingstochastic variability ordering

Mathematics Subject Classification ID

Sequential statistical design (62L05) Bayesian problems; characterization of Bayes procedures (62C10)

Recommendations

• Worth of perfect information in bernoulli bandits
• On the Worth of Perfect Information in Bandits with Random Discounting
• scientific article; zbMATH DE number 4059270
• A class of bandit problems yielding myopic optimal strategies

Cites work

• scientific article; zbMATH DE number 4078557 (Why is no real title available?)
• scientific article; zbMATH DE number 605729 (Why is no real title available?)
• A Bernoulli Two-armed Bandit
• The learning component of dynamic allocation indices

Cited in

(2)

• Robustness of stochastic bandit policies
• Worth of perfect information in bernoulli bandits

This page was built for publication: Bandit bounds from stochastic variability extrema

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1373975)