Policy set iteration for Markov decision processes

DOI10.1016/J.AUTOMATICA.2013.09.010MaRDI QIDQ2350853zbMATH OpenOpenAlexFDO

Authors Hyeong Soo Chang

Publication date 25 June 2015

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.automatica.2013.09.010

zbMATH Keywords

dynamic programmingMarkov decision processespolicy iterationrandomization

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40) Stochastic systems in control theory (general) (93E03)

Recommendations

• Value set iteration for Markov decision processes
• Policy iteration for robust nonstationary Markov decision processes
• A note on policy algorithms for discounted Markov decision problems
• On the Convergence of Policy Iteration in Finite State Undiscounted Markov Decision Processes: The Unichain Case
• Adaptive policy-iteration and policy-value-iteration for discounted Markov decision processes

Cited in

(11)

• Reduced complexity dynamic programming based on policy iteration
• Policy iteration type algorithms for recurrent state Markov decision processes
• Interval iteration algorithm for MDPs and IMDPs
• scientific article; zbMATH DE number 5547972 (Why is no real title available?)
• Adaptive policy-iteration and policy-value-iteration for discounted Markov decision processes
• A new policy iteration scheme for Markov decision processes using Schweitzer's formula
• Set coverage and robust policy
• Value set iteration for Markov decision processes
• Policy iteration for robust nonstationary Markov decision processes
• Multi-policy iteration with a distributed voting.
• Random search for constrained Markov decision processes with multi-policy improvement

This page was built for publication: Policy set iteration for Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2350853)