Some optimal strategies for bandit problems with beta prior distributions

DOI10.1023/A:1004130209258MaRDI QIDQ1585898zbMATH OpenOpenAlexFDO

Authors Chien-Tai Lin, C. J. Shiau

Publication date 2000

Published in Annals of the Institute of Statistical Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1023/a:1004130209258

zbMATH Keywords

dynamic allocation of Bernoulli processessequential experimentationBandit problemsk-failure strategym-run strategyN-learning strategynon-recalling m-run strategystaying-with-a-winnerswitching-on-a-loser

Mathematics Subject Classification ID

Bayesian inference (62F15) Sequential statistical design (62L05)

Recommendations

• A note on infinite-armed Bernoulli bandit problems with generalized beta prior distributions
• A note on strategies for bandit problems with infinitely many arms
• Optimal Bayesian strategies for the infinite-armed Bernoulli bandit
• Bandit problems with infinitely many arms
• Some monotonicity properties of parametric and nonparametric Bayesian bandits

Cited in

(5)

• scientific article; zbMATH DE number 6276176 (Why is no real title available?)
• A note on infinite-armed Bernoulli bandit problems with generalized beta prior distributions
• A conjecture on the Feldman bandit problem
• Optimal Bayesian strategies for the infinite-armed Bernoulli bandit
• A note on strategies for bandit problems with infinitely many arms

This page was built for publication: Some optimal strategies for bandit problems with beta prior distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1585898)