An optimal stopping zero-sum game in discrete-time multi-armed bandit processes

DOI10.1080/02522667.1998.10699387zbMath0957.91031OpenAlexW1988645820MaRDI QIDQ4256753

Yuji Yoshida

Publication date: 2 August 1999

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

Full work available at URL: https://doi.org/10.1080/02522667.1998.10699387

zbMATH Keywords

zero-sum gamesBellman's equationoptimal stopping timesMarkov strategiesmulti-armed bandit processesoptimal Markov strategiesMarkov stopping timesbandit games

Mathematics Subject Classification ID

Game theory (91A99) Discrete-time games (91A50) Decision theory for games (91A35)

Cites Work

• Markov strategies for optimal control problems indexed by a partially ordered set
• Discrete multiarmed bandits and multiparameter processes
• Optimal stopping and supermartingales over partially ordered sets

This page was built for publication: An optimal stopping zero-sum game in discrete-time multi-armed bandit processes