Detecting optimal and non-optimal actions in average-cost Markov decision processes

DOI10.2307/3215322zbMATH Open0815.60061OpenAlexW2330034154MaRDI QIDQ4322051

Jean B. Lasserre

Publication date: 20 March 1995

Published in: Journal of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.2307/3215322

zbMATH Keywords

linear programmingpolicy iterationelimination of non-optimal actions

Mathematics Subject Classification ID

Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)

Recommendations

• Title not available (Why is that?) 👍 👎
• Title not available (Why is that?) 👍 👎
• Optimal policies for constrained average-cost Markov decision processes 👍 👎
• Average cost Markov decision processes: Optimality conditions 👍 👎
• Verifiable conditions for average optimality of continuous-time Markov decision processes 👍 👎
• Detection-averse optimal and receding-horizon control for Markov decision processes 👍 👎
• On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes 👍 👎
• Optimality Conditions for Partially Observable Markov Decision Processes 👍 👎
• Markov decision processes in minimization of expected costs 👍 👎

This page was built for publication: Detecting optimal and non-optimal actions in average-cost Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4322051)