Finite-stage reward functions having the Markov adequacy property

DOI10.1016/0304-4149(93)90088-LMaRDI QIDQ1802324zbMATH OpenOpenAlexFDO

Authors Xiaobo Wang, Victor C. Pestien

Publication date 9 December 1993

Published in Stochastic Processes and their Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0304-4149(93)90088-l

zbMATH Keywords

countable state spacebounded rewardrandomized Markov strategy

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• The existence of good Markov strategies for decision processes with general payoffs
• On Stationary Strategies in Countable State Total Reward Markov Decision Processes
• On Stationary Strategies in Borel Dynamic Programming
• The finiteness of the reward function and the optimal value function in Markov decision processes
• An expected average reward criterion

Cites work

• scientific article; zbMATH DE number 3860907 (Why is no real title available?)
• scientific article; zbMATH DE number 3560402 (Why is no real title available?)
• scientific article; zbMATH DE number 3434895 (Why is no real title available?)
• Controlled Markov Processes with Arbitrary Numerical Criteria
• Markov Strategies in Dynamic Programming
• Negative Dynamic Programming
• Non-Randomized Markov and Semi-Markov Strategies in Dynamic Programming
• On the Existence of Good Markov Strategies
• Stationary policies and Markov policies in Borel dynamic programming
• The existence of good Markov strategies for decision processes with general payoffs

Cited in

(1)

• Markov-achievable payoffs for finite-horizon decision models.

This page was built for publication: Finite-stage reward functions having the Markov adequacy property

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1802324)