The system of quasi-variational inequalities attached to the two-armed bandit problem

DOI10.1080/17442509408833888MaRDI QIDQ4840928zbMATH OpenOpenAlexFDO

Authors Teruo Tanaka

Publication date 14 November 1995

Published in Stochastics and Stochastic Reports (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/17442509408833888

zbMATH Keywords

Dirichlet formsGittins indexvariational inequalityquasi-variational inequalitiesstochastic control problemsdegenerate diffusion processesbi-Markov processestwo-parameter continuous time stochastic processestwo-parameter optimal stopping problem

Mathematics Subject Classification ID

Continuous-time Markov processes on general state spaces (60J25) Optimal stochastic control (93E20)

Recommendations

• Stochastic control of two-parameter processes application:the two-armed bandit problem
• scientific article; zbMATH DE number 3934122
• Stochastic control of symmetric markov processes and nonlinear variational inequalities
• scientific article; zbMATH DE number 3894967
• scientific article; zbMATH DE number 3865129

Cites work

• scientific article; zbMATH DE number 3656300 (Why is no real title available?)
• scientific article; zbMATH DE number 3751685 (Why is no real title available?)
• scientific article; zbMATH DE number 3507496 (Why is no real title available?)
• scientific article; zbMATH DE number 194374 (Why is no real title available?)
• scientific article; zbMATH DE number 3272022 (Why is no real title available?)
• Continuous multi-armed bandits and multiparameter processes
• Gittins indices in the dynamic allocation problem for diffusion processes
• On an optimal stopping problem and a variational inequality
• On the Optimal Impulse Control Problem for Degenerate Diffusions
• On the Optimal Reward Function of the Continuous Time Multiarmed Bandit Problem
• On the Optimal Stopping Time Problem for Degenerate Diffusions
• Optimal switching for alternating processes
• Optimal switching for two-parameter stochastic processes
• Stochastic control of two-parameter processes application:the two-armed bandit problem
• Two parameter optimal stopping and bi-Markov processes

This page was built for publication: The system of quasi-variational inequalities attached to the two-armed bandit problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4840928)