A dynamic programming strategy to balance exploration and exploitation in the bandit problem

DOI10.1007/S10472-010-9190-1MaRDI QIDQ647433zbMATH OpenOpenAlexFDO

Authors Olivier Caelen, Gianluca Bontempi

Publication date 23 November 2011

Published in Annals of Mathematics and Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10472-010-9190-1

zbMATH Keywords

estimationgreedymulti-armed bandit problem

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Estimation in multivariate analysis (62H12) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Recommendations

• Optimal exploration-exploitation in a multi-armed bandit problem with non-stationary rewards
• scientific article; zbMATH DE number 1907146
• Finite-time analysis of the multiarmed bandit problem
• Pure exploration in multi-armed bandits problems
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems

Cites work

• scientific article; zbMATH DE number 4061056 (Why is no real title available?)
• scientific article; zbMATH DE number 1306865 (Why is no real title available?)
• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 708500 (Why is no real title available?)
• scientific article; zbMATH DE number 194374 (Why is no real title available?)
• A dynamic programming strategy to balance exploration and exploitation in the bandit problem
• Approximate Dynamic Programming
• Exploration of multi-state environments: Local measures and back-propagation of uncertainty
• Finite-time analysis of the multiarmed bandit problem
• Pattern recognition and machine learning.
• Some aspects of the sequential design of experiments
• The sample average approximation method for stochastic discrete optimization

Cited in

(2)

• Infomax strategies for an optimal balance between exploration and exploitation
• A dynamic programming strategy to balance exploration and exploitation in the bandit problem

Describes a project that uses

Uses Software

• PRMLT
• bootstrap

This page was built for publication: A dynamic programming strategy to balance exploration and exploitation in the bandit problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q647433)