Optimal strategy for Bayesian two-armed bandit problem with an arched reward function

DOI10.3934/MCRF.2022057MaRDI QIDQ6127344zbMATH OpenOpenAlexFDO

Authors Zengjing Chen, Zhao-Ang Zhang

Publication date 12 April 2024

Published in Mathematical Control and Related Fields (Search for Journal in Brave)

Full work available at URL https://doi.org/10.3934/mcrf.2022057

zbMATH Keywords

Bayesian two-armed banditdynamic programminglaw of large numbersmyopic strategyoptimal strategysequential design

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Bayesian problems; characterization of Bayes procedures (62C10) Sequential statistical design (62L05) Dynamic programming (90C39)

Recommendations

• Optimal Bayesian strategies for the infinite-armed Bernoulli bandit
• A class of bandit problems yielding myopic optimal strategies
• Small-sample performance of Bernoulli two-armed bandit Bayesian strategies
• A Note on Optimal Strategies of a Generalized Two-Stage Bandit Problem
• Solving two-armed Bernoulli bandit problems using a Bayesian learning automaton

This page was built for publication: Optimal strategy for Bayesian two-armed bandit problem with an arched reward function

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6127344)