Average optimal stationary policies and linear programming in countable space Markov decision processes

DOI10.1006/JMAA.1994.1143zbMATH Open0820.90125OpenAlexW2116933821MaRDI QIDQ1329326FDOQ1329326

Authors: Jean B. Lasserre 

Publication date: 4 July 1994

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

Full work available at URL: https://doi.org/10.1006/jmaa.1994.1143

Recommendations

• Linear programming formulation of MDPs in countable state space: The multichain case
• A new condition for the existence of optimal stationary policies in average cost Markov decision processes
• scientific article; zbMATH DE number 3860907
• A note on the existence of optimal stationary policies for average Markov decision processes with countable states
• The LP approach in average reward MDPs with multiple cost constraints: The countable state case

zbMATH Keywords

infinite-dimensional linear programaverage optimal stationary policiescountable space Markov decision processes

Mathematics Subject Classification ID

Linear programming (90C05) Markov and semi-Markov decision processes (90C40) Programming in abstract spaces (90C48)

Cited In (9)

• A semimartingale characterization of average optimal stationary policies for Markov decision processes
• Maximizing the probability of visiting a set infinitely often for a countable state space Markov decision process
• Optimal service control against worst case admission policies: A multichained stochastic game
• Linear programming formulation of MDPs in countable state space: The multichain case
• A note on the existence of optimal stationary policies for average Markov decision processes with countable states
• Duality in Markov Decision Problems with Countable Action and State Spaces
• Title not available (Why is that?)
• Existence of Optimal Policies for Semi-Markov Decision Processes Using Duality for Infinite Linear Programming
• On linear programming for constrained and unconstrained average-cost Markov decision processes with countable action spaces and strictly unbounded costs

This page was built for publication: Average optimal stationary policies and linear programming in countable space Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1329326)