A new class of policies in vector-valued Markov decision processes

DOI10.1006/jmaa.1996.0337zbMath0856.90125OpenAlexW2083772885MaRDI QIDQ1922948

Kazuyoshi Wakuta

Publication date: 30 September 1996

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jmaa.1996.0337

zbMATH Keywords

discounted reward criterionvector-valued Markov decision processcombination of optimal stationary policies

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (2)

Discounted Cost Markov Decision Processes with a Constraint ⋮ Neighbourhood search for constructing Pareto sets

This page was built for publication: A new class of policies in vector-valued Markov decision processes