Bandit problems with infinitely many arms

DOI10.1214/AOS/1069362389MaRDI QIDQ1374228zbMATH OpenOpenAlexFDO

Authors Donald A. Berry, Robert W. Chen, Alan Zame, David Heath, Larry Shepp

Publication date 22 February 1998

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

Full work available at URL https://doi.org/10.1214/aos/1069362389

zbMATH Keywords

bandit problemdynamic allocation of Bernoulli processessequential experimentationstaying with a winnerswitching with a loser

Mathematics Subject Classification ID

Sequential statistical design (62L05) Compound decision problems in statistical decision theory (62C25) Limit theorems in probability theory (60F99)

Recommendations

• A note on strategies for bandit problems with infinitely many arms
• scientific article; zbMATH DE number 3967731
• The Irrevocable Multiarmed Bandit Problem
• Infinite Arms Bandit: Optimality via Confidence Bounds
• The Continuum-Armed Bandit Problem
• scientific article; zbMATH DE number 4059270
• Denumerable-Armed Bandits

Cited in

(18)

• Optimal Bayesian strategies for the infinite-armed Bernoulli bandit
• scientific article; zbMATH DE number 3967731 (Why is no real title available?)
• Finding minimax strategy and minimax risk for Bernoulli multi-armed bandit
• Satisficing in Time-Sensitive Bandit Learning
• Randomized allocation with nonparametric estimation for a multi-armed bandit problem with covariates
• Multinomial Thompson sampling for rating scales and prior considerations for calibrating uncertainty
• A note on infinite-armed Bernoulli bandit problems with generalized beta prior distributions
• A note on strategies for bandit problems with infinitely many arms
• Infinite Arms Bandit: Optimality via Confidence Bounds
• A conjecture on the Feldman bandit problem
• The Irrevocable Multiarmed Bandit Problem
• Bandit and covariate processes, with finite or non-denumerable set of arms
• Topp-Leone distribution with an application to binomial sampling
• Ballooning multi-armed bandits
• Policies without Memory for the Infinite-Armed Bernoulli Bandit under the Average-Reward Criterion
• Two-Armed Bandit Strategies that Discount Past and Future
• Multi-armed bandit experiments in the online service economy
• Some optimal strategies for bandit problems with beta prior distributions

This page was built for publication: Bandit problems with infinitely many arms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1374228)