Isotone optimal policies for structured Markov decision processes

DOI10.1016/0377-2217(81)90098-9zbMath0455.90090OpenAlexW2064637452MaRDI QIDQ1150313

Douglas J. White

Publication date: 1981

Published in: European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0377-2217(81)90098-9

zbMATH Keywords

semi-Markov decision processesisotone optimal policiespolicy space algorithmspecial state spacestructured Markov decision processesvalue iteration method

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (1)

Negatively isotone optimal policies for random walk type Markov decision processes

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Finite state approximation for denumerable-state infinite horizon contracted Markov decision processes: The policy space method
• On the Optimality of Structured Policies in Countable Stage Decision Processes
• Contraction Mappings in the Theory Underlying Dynamic Programming

This page was built for publication: Isotone optimal policies for structured Markov decision processes