On nearly selfoptimizing strategies for multiarmed bandit problems with controlled arms

DOI10.4064/AM-23-4-449-473MaRDI QIDQ4879862zbMATH OpenOpenAlexFDO

Authors Ewa Drabik

Publication date 2 June 1996

Published in Applicationes Mathematicae (Search for Journal in Brave)

Full work available at URL https://eudml.org/doc/219145

zbMATH Keywords

adaptive controlinvariant measurestochastic controlmultiarmed Markov bandit problemselfoptimizing strategies

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Optimal stochastic control (93E20) Stochastic learning and adaptive control (93E35)

Recommendations

• The multi-armed bandit, with constraints
• Optimal stopping problems for multiarmed bandit processes with arms' independence
• scientific article; zbMATH DE number 4064878
• Combining multiple strategies for multiarmed bandit problems and asymptotic optimality
• Generalized Bandit Problems

Cited in

(3)

• Combining multiple strategies for multiarmed bandit problems and asymptotic optimality
• scientific article; zbMATH DE number 3918239 (Why is no real title available?)
• scientific article; zbMATH DE number 7596797 (Why is no real title available?)

This page was built for publication: On nearly selfoptimizing strategies for multiarmed bandit problems with controlled arms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4879862)