A doscounted uniform one-armed bandit problem

DOI10.1080/07474949208836241zbMath0748.62042OpenAlexW1966724437MaRDI QIDQ4008951

Toshio Hamada

Publication date: 27 September 1992

Published in: Sequential Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/07474949208836241

zbMATH Keywords

optimal strategyuniform distributionPareto distributiondiscount factorbandit problemBayesian updatingmyopic strategycritical value functiontotal expected discounted sum of the observations

Mathematics Subject Classification ID

Applications of mathematical programming (90C90) Dynamic programming (90C39) Sequential statistical design (62L05) Optimal stopping in statistics (62L15)

Cites Work

• Some best possible results for a discounted one armed bandit
• Der diskontierte einarmige Bandit
• Optimality of myopic stopping times for geometric discounting

This page was built for publication: A doscounted uniform one-armed bandit problem