The variational calculus and approximation in policy space for Markovian decision processes

DOI10.1016/0022-247X(85)90197-0zbMath0579.90097MaRDI QIDQ1068009

Paul J. Schweitzer

Publication date: 1985

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

zbMATH Keywords

variational calculusgain ratestate valuessuccessive approximations in policy space

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Markov and semi-Markov decision processes (90C40)

Cites Work

• The Functional Equations of Undiscounted Markov Renewal Programming
• On the Convergence of Policy Iteration in Stationary Dynamic Programming
• Markov-Renewal Programming. I: Formulation, Finite Return Models
• On Finding Optimal Policies in Discrete Dynamic Programming with No Discounting
• Perturbation Theory and Undiscounted Markov Renewal Programming
• Algorithms for Stochastic Games with Geometrical Interpretation
• Discrete Dynamic Programming with Sensitive Discount Optimality Criteria
• Perturbation theory and finite Markov chains
• Markov Renewal Programs with Small Interest Rates
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: The variational calculus and approximation in policy space for Markovian decision processes