A new policy iteration scheme for Markov decision processes using Schweitzer's formula

DOI10.2307/3215254zbMATH Open0796.60074OpenAlexW4245522021MaRDI QIDQ4296391

Jean B. Lasserre

Publication date: 20 September 1994

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

Full work available at URL: https://doi.org/10.2307/3215254

zbMATH Keywords

Markov chainsMarkov decision processespolicy iterationfinite-state Markov chainssteady-state probabilitiesfundamental matricesperturbation theory of Markov chains

Mathematics Subject Classification ID

Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Markov and semi-Markov decision processes (90C40)

Related Items (2)

Policy iteration for continuous-time average reward Markov decision processes in Polish spaces ⋮ A New Policy Evaluation Algorithm for Markov Decision Processes with Quasi Birth-Death Structure

Recommendations

• Title not available (Why is that?) 👍 👎
• Policy iteration for robust nonstationary Markov decision processes 👍 👎
• The policy iteration algorithm for average continuous control of piecewise deterministic Markov processes 👍 👎
• Policy iteration and Newton-Raphson methods for Markov decision processes under average cost criterion 👍 👎
• Policy iteration type algorithms for recurrent state Markov decision processes 👍 👎
• A new class of policies in vector-valued Markov decision processes 👍 👎
• Policy set iteration for Markov decision processes 👍 👎
• The policy iteration algorithm for average reward Markov decision processes with general state space 👍 👎

This page was built for publication: A new policy iteration scheme for Markov decision processes using Schweitzer's formula

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4296391)