Policy iteration and Newton-Raphson methods for Markov decision processes under average cost criterion

DOI10.1016/0898-1221(92)90240-IMaRDI QIDQ1206121zbMATH OpenOpenAlexFDO

Authors Masamitsu Ohnishi

Publication date 1 April 1993

Published in Computers & Mathematics with Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0898-1221(92)90240-i

zbMATH Keywords

average cost criterionNewton-Raphson methodspolicy iteration

Mathematics Subject Classification ID

Computational methods for problems pertaining to operations research and mathematical programming (90-08) Fractional programming (90C32) Markov and semi-Markov decision processes (90C40)

Recommendations

• Policy Improvement and the Newton-Raphson Algorithm
• A New Value Iteration method for the Average Cost Dynamic Programming Problem
• Policy iteration type algorithms for recurrent state Markov decision processes
• The policy iteration algorithm for average reward Markov decision processes with general state space
• Average optimality for continuous-time Markov decision processes with a policy iteration approach

Cites work

• A Class of Decision Processes Showing Policy-Improvement/Newton–Raphson Equivalence
• A simple technique in Markovian control with applications to resource allocation to resource allocation in communication networks
• Contraction Mappings in the Theory Underlying Dynamic Programming
• Finite state Markovian decision processes
• Fractional programming
• scientific article; zbMATH DE number 3885030 (Why is no real title available?)
• scientific article; zbMATH DE number 3148886 (Why is no real title available?)
• scientific article; zbMATH DE number 4154239 (Why is no real title available?)
• scientific article; zbMATH DE number 3906232 (Why is no real title available?)
• scientific article; zbMATH DE number 4061056 (Why is no real title available?)
• scientific article; zbMATH DE number 4064435 (Why is no real title available?)
• scientific article; zbMATH DE number 3718878 (Why is no real title available?)
• scientific article; zbMATH DE number 3333895 (Why is no real title available?)
• scientific article; zbMATH DE number 3338194 (Why is no real title available?)
• On the Convergence of Policy Iteration in Finite State Undiscounted Markov Decision Processes: The Unichain Case
• On the Convergence of Policy Iteration in Stationary Dynamic Programming
• Policy Improvement and the Newton-Raphson Algorithm
• Policy Improvement and the Newton–Raphson Algorithm for Renewal Reward Processes

Cited in

(7)

• Policy Improvement and the Newton-Raphson Algorithm
• Policy Improvement and the Newton–Raphson Algorithm for Renewal Reward Processes
• A Class of Decision Processes Showing Policy-Improvement/Newton–Raphson Equivalence
• A fifth bibliography of fractional programming^*
• A new policy iteration scheme for Markov decision processes using Schweitzer's formula
• A New Value Iteration method for the Average Cost Dynamic Programming Problem
• Optimal policy for a production-inventory system with setup cost and average cost criterion

This page was built for publication: Policy iteration and Newton-Raphson methods for Markov decision processes under average cost criterion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1206121)