The Compactness of a Policy Space in Dynamic Programming Via an Extension Theorem for Carathéodory Functions

DOI10.1287/MOOR.22.2.458MaRDI QIDQ4346231zbMATH OpenOpenAlexFDO

Authors Alexander A. Yushkevich

Publication date 9 December 1998

Published in Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1287/moor.22.2.458

zbMATH Keywords

compactness theoremCarathéodory functionsoptimal policies in stochastic dynamic programmingset of measures on a subset of a product space

Mathematics Subject Classification ID

Dynamic programming (90C39) Dynamic programming in optimal control and differential games (49L20)

Recommendations

• On compactness of the space of policies in stochastic dynamic programming
• A note on the existence of optimal policies in total reward dynamic programs with compact action sets.
• Compactness of the space of non-randomized policies in countable-state sequential decision processes
• scientific article; zbMATH DE number 703928
• Stationary Policies in Dynamic Programming Models Under Compactness Assumptions
• A Note on the Convergence of Policy Iteration in Markov Decision Processes with Compact Action Spaces
• Existence Without Explicit Compactness in Stochastic Dynamic Programming
• Approximate dynamic programming for stochastic linear control problems on compact state spaces
• On undiscounted markovian decision processes with compact action spaces
• scientific article; zbMATH DE number 4003938

Cited in

(8)

• On compactness of the space of policies in stochastic dynamic programming
• A note on the existence of optimal policies in total reward dynamic programs with compact action sets.
• Compactness of the space of non-randomized policies in countable-state sequential decision processes
• Nowak's Theorem on Probability Measures Induced by Strategies Revisited
• scientific article; zbMATH DE number 4108536 (Why is no real title available?)
• Sufficiency of deterministic policies for atomless discounted and uniformly absorbing MDPs with multiple criteria
• Optimal policies for constrained average-cost Markov decision processes
• A linear programming formulation for constrained discounted continuous control for piecewise deterministic Markov processes

This page was built for publication: The Compactness of a Policy Space in Dynamic Programming Via an Extension Theorem for Carathéodory Functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4346231)