Average cost Markov decision processes under the hypothesis of Doeblin

DOI10.1007/BF02283606zbMath0738.90085OpenAlexW2090383517MaRDI QIDQ1174703

Masami Kurano

Publication date: 25 June 1992

Published in: Annals of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf02283606

zbMATH Keywords

Doeblin conditionoptimal stationary policyaverage cost criterionbounded lower semicontinuous cost functionscompact state and action spaces

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (5)

Existence of optimal stationary policies in discounted Markov decision processes: Approaches by occupation measures ⋮ Recurrence conditions for Markov decision processes with Borel state space: A survey ⋮ On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes ⋮ Asymptotic behavior of continuous stochastic games ⋮ Functional characterization for average cost Markov decision processes with Doeblin's conditions

Cites Work

• Unnamed Item
• Stochastic optimal control. The discrete time case
• On Minimum Cost Per Unit Time Control of Markov Chains
• Markov Decision Processes with a Borel Measurable Cost Function—The Average Case
• The Existence of a Minimum Pair of State and Policy for Markov Decision Processes under the Hypothesis of Doeblin
• Stationary Markovian Decision Problems and Perturbation Theory of Quasi-Compact Linear Operators
• Negative Dynamic Programming
• Arbitrary State Markovian Decision Processes

This page was built for publication: Average cost Markov decision processes under the hypothesis of Doeblin