Separable value functions for infinite horizon average reward Markov decision processes

DOI10.1016/0022-247X(89)90345-4zbMath0693.90095MaRDI QIDQ908861

Douglas J. White

Publication date: 1989

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

zbMATH Keywords

infinite horizonaverage rewardMarkov decision problemoptimality equationexpected rewardseparated optimality equations

Mathematics Subject Classification ID

Inventory, storage, reservoirs (90B05) Markov and semi-Markov decision processes (90C40)

Cites Work

• Unnamed Item
• Managing stochastic multispecies models
• Optimal harvesting strategies for stochastic single-species, multiage class models
• Finite state Markovian decision processes
• Policy Bounds for Markov Decision Processes
• The Asymptotic Behavior of Undiscounted Value Iteration in Markov Decision Problems
• On the Iterative Method of Dynamic Programming on a Finite Space Discrete Time Markov Process
• Optimal Policy for a Multi-Product, Dynamic, Nonstationary Inventory Problem

This page was built for publication: Separable value functions for infinite horizon average reward Markov decision processes