Two-stage bandits

DOI10.1214/AOS/1176350841MaRDI QIDQ1115072zbMATH OpenOpenAlexFDO

Authors Murray K. Clayton, Jeffrey A. Witmer

Publication date 1988

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

Full work available at URL https://doi.org/10.1214/aos/1176350841

zbMATH Keywords

dichotomous responsesOptimal strategiesrandom discount sequenceregular discountingsequential decisionstwo-stage bandittwo-stage decision problem

Mathematics Subject Classification ID

Bayesian problems; characterization of Bayes procedures (62C10) Sequential statistical analysis (62L10)

Review text

Two stochastic processes, or ``arms, that yield dichotomous responses are available for use in a two-stage decision problem. During the first stage, arms are chosen sequentially; the resulting observations are discounted by a fixed value \(\beta\). A single arm must be used in the second stage, in which observations are not discounted. The decision to end the first stage is based on the data obtained. Optimal strategies are considered in the presence of the random discount sequence that arises in this setting. This extends the work of \textit{D. A. Berry} and \textit{B. Fristedt} [Ann. Stat. 7, 1086-1105 (1979; Zbl 0415.62056)].

Recommendations

• Two-armed Dirichlet bandits with discounting
• A TWO-ARMED BANDIT PROBLEM WITH ONE ARM KNOWN UNDER SOME CONSTRAINTS
• Multistage bandit problems
• A Note on Optimal Strategies of a Generalized Two-Stage Bandit Problem
• scientific article; zbMATH DE number 3942837

Cited in

(12)

• Optimal few-stage designs
• Evaluation of asymptotic approximations for a two-stage Bernoulli bandit
• Two-armed Dirichlet bandits with discounting
• A Note on Optimal Strategies of a Generalized Two-Stage Bandit Problem
• Sequential allocation in clinical trials
• scientific article; zbMATH DE number 3854141 (Why is no real title available?)
• Covariate models for bernoulli bandits
• On a sequential two-action decision model¹with unbounded reward functions
• Generalized two-stage bandit problem
• scientific article; zbMATH DE number 733898 (Why is no real title available?)
• The prediction distribution for the heteroscedastic multivariate lineary models
• Modifications in the discount sequence for bandit processes

This page was built for publication: Two-stage bandits

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1115072)