Foolproof convergence in multichain policy iteration

DOI10.1016/0022-247X(78)90044-6MaRDI QIDQ1245162zbMATH OpenFDO

Authors Paul J. Schweitzer, Awi Federgruen

Publication date 1978

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

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cites work

• scientific article; zbMATH DE number 3148886 (Why is no real title available?)
• Discrete Dynamic Programming
• Markov-Renewal Programming. I: Formulation, Finite Return Models
• Multichain Markov Renewal Programs
• Perturbation Theory and Undiscounted Markov Renewal Programming
• Perturbation theory and finite Markov chains
• Potentials for denumerable Markov chains
• The Functional Equations of Undiscounted Markov Renewal Programming

Cited in

(3)

• A further anticycling rule in multichain policy iteration for undiscounted Markov renewal programs
• A value-iteration scheme for undiscounted multichain Markov renewal programs
• A unified approach to Markov decision problems and performance sensitivity analysis with discounted and average criteria: multichain cases

This page was built for publication: Foolproof convergence in multichain policy iteration

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1245162)