Bernoulli one-armed bandits - Arbitrary discount sequences

DOI10.1214/AOS/1176344792MaRDI QIDQ600201zbMATH OpenOpenAlexFDO

Authors Donald A. Berry, Bert E. Fristedt

Publication date 1979

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1214/aos/1176344792

zbMATH Keywords

optimal stoppingoptimal strategysequential decisionBernoulli banditone-armed banditregular discountingtwo-armed bandit

Mathematics Subject Classification ID

Sequential statistical design (62L05) Optimal stopping in statistics (62L15)

Cited in

(10)

• Covariate models for bernoulli bandits
• Two-Armed Bandit Strategies that Discount Past and Future
• The prediction distribution for the heteroscedastic multivariate lineary models
• Bayesian bandits in clinical trials
• Multistage decission problems
• A Note on Optimal Strategies of a Generalized Two-Stage Bandit Problem
• Maximizing the length of a success run for many-armed bandits
• Bernoulli two-armed bandits with geometric termination
• A Note on Dirichlet One-Armed Bandits
• Generalized two-stage bandit problem

This page was built for publication: Bernoulli one-armed bandits - Arbitrary discount sequences

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q600201)