Zero-sum Games for Discrete-time Multi-armed Bandit Processes with a Generalized Discount

DOI10.1080/02522667.1992.10699109MaRDI QIDQ4024144zbMATH OpenOpenAlexFDO

Authors Yuji Yoshida

Publication date 25 February 1993

Published in Journal of Information and Optimization Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/02522667.1992.10699109

zbMATH Keywords

Bellman's equationmulti-armed bandit processesmulti-parameter Markov processesvalue iteration

Mathematics Subject Classification ID

2-person games (91A05) Stochastic games, stochastic differential games (91A15)

Recommendations

• An optimal stopping zero-sum game in discrete-time multi-armed bandit processes
• scientific article; zbMATH DE number 4211191
• Zero-sum Markov games with random state-actions-dependent discount factors: existence of optimal strategies
• scientific article; zbMATH DE number 3876959
• Asymptotically optimal strategies for adaptive zero-sum discounted Markov games

Cites work

• Discrete multiarmed bandits and multiparameter processes
• Evaluating strategies for generalized bandit problems
• scientific article; zbMATH DE number 194374 (Why is no real title available?)
• Markov strategies for optimal control problems indexed by a partially ordered set
• Optimal stopping and supermartingales over partially ordered sets

Cited in

(3)

• Playing in stochastic environment: from multi-armed bandits to two-player games
• scientific article; zbMATH DE number 4211191 (Why is no real title available?)
• An optimal stopping zero-sum game in discrete-time multi-armed bandit processes

This page was built for publication: Zero-sum Games for Discrete-time Multi-armed Bandit Processes with a Generalized Discount

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4024144)