scientific article; zbMATH DE number 3891133

MaRDI QIDQ3347666zbMATH OpenFDO

Authors Sanja Djurinović

Publication date 1985

zbMATH Keywords

discrete Markov decision processefficient policiesfinite state and action spacemultiple expected average cost criteriaoptimal solution

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• scientific article; zbMATH DE number 4003940
• Optimal policies for constrained average-cost Markov decision processes
• Markov decision processes with multiple costs
• An Algorithm to Identify and Compute Average Optimal Policies in Multichain Markov Decision Processes
• Markov decision processes: Discounted expected reward or average expected reward?

Cited in

(7)

• Markov decision processes with multidimensional action spaces
• Functional characterization for average cost Markov decision processes with Doeblin's conditions
• Markov decision processes: Discounted expected reward or average expected reward?
• scientific article; zbMATH DE number 4003940 (Why is no real title available?)
• Detecting optimal and non-optimal actions in average-cost Markov decision processes
• An Algorithm to Identify and Compute Average Optimal Policies in Multichain Markov Decision Processes
• Markov decision processes with multiple costs

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3347666)