Isotone policies for the value iteration method for Markov decision processes

DOI10.1007/BF01720072MaRDI QIDQ800232zbMATHFDO

Authors D. J. White

Publication date 1984

Published in OR Spektrum (Search for Journal in Brave)

zbMATH Keywords

countable state discounted Markov decision processesN-isotone sequence of optimal decision rulesN-isotonicityvalue iteration process

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• Discount-isotone policies for Markov decision processes
• The value iteration method for countable state Markov decision processes
• scientific article; zbMATH DE number 3916050
• Monotone value iteration for discounted finite Markov decision processes
• Value iteration in countable state average cost Markov decision processes with unbounded costs

Cites work

• scientific article; zbMATH DE number 3670172 (Why is no real title available?)
• Discounted Dynamic Programming
• Markov programming by successive approximations with respect to weighted supremum norms
• Minimizing a Submodular Function on a Lattice

Cited in

(1)

• Discount-isotone policies for Markov decision processes

This page was built for publication: Isotone policies for the value iteration method for Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q800232)