The N-armed bandit with unimodal structure

DOI10.1007/BF02056924zbMath0519.62066OpenAlexW2089068924MaRDI QIDQ1054428

Ulrich Herkenrath

Publication date: 1983

Published in: Metrika (Search for Journal in Brave)

Full work available at URL: https://eudml.org/doc/175907

zbMATH Keywords

multi-armed bandit problemunimodal structure of expected rewards

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Stochastic approximation (62L20) Sequential statistical design (62L05)

Related Items (3)

Weighted \(L_{\infty}\) isotonic regression ⋮ On integer stochastic approximation ⋮ Optimizing a Unimodal Response Function for Binary Variables

Cites Work

• Unnamed Item
• Unnamed Item
• The apparent conflict between estimation and control - a survey of the two-armed bandit problem
• Randomised allocation of treatments in sequential trials
• Stochastic Approximation of Minima with Improved Asymptotic Speed
• Some aspects of the sequential design of experiments

This page was built for publication: The N-armed bandit with unimodal structure