A Class of Decision Processes Showing Policy-Improvement/Newton–Raphson Equivalence

DOI10.1017/S0269964800001261MaRDI QIDQ3415941zbMATH OpenFDO

Authors Peter Whittle

Publication date 19 January 2007

Published in Probability in the Engineering and Informational Sciences (Search for Journal in Brave)

Mathematics Subject Classification ID

Generalized linear models (logistic models) (62J12) Markov and semi-Markov decision processes (90C40)

Recommendations

• Policy Improvement and the Newton-Raphson Algorithm
• Policy Improvement and the Newton–Raphson Algorithm for Renewal Reward Processes
• Policy iteration and Newton-Raphson methods for Markov decision processes under average cost criterion
• Approximate Newton methods for policy search in Markov decision processes
• On the Complexity of the Policy Improvement Algorithm for Markov Decision Processes
• On the policy improvement algorithm in continuous time
• A Policy Improvement Method in Constrained Stochastic Dynamic Programming
• Approximate Newton Policy Gradient Algorithms
• Policy iterations for reinforcement learning problems in continuous time and space -- fundamental theory and methods
• Approximate policy iteration: a survey and some new methods

Cites work

• Risk-sensitive linear/quadratic/gaussian control

Cited in

(3)

• Policy Improvement and the Newton-Raphson Algorithm
• Policy Improvement and the Newton–Raphson Algorithm for Renewal Reward Processes
• Policy iteration and Newton-Raphson methods for Markov decision processes under average cost criterion

This page was built for publication: A Class of Decision Processes Showing Policy-Improvement/Newton–Raphson Equivalence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3415941)