Strong 0-discount optimal policies in a Markov decision process with a Borel state space

DOI10.1007/BF01415675zbMath0838.90136MaRDI QIDQ4845096

Alexander A. Yushkevich

Publication date: 4 September 1995

Published in: [https://portal.mardi4nfdi.de/entity/Q3031760 ZOR Zeitschrift f�r Operations Research Methods and Models of Operations Research] (Search for Journal in Brave)

zbMATH Keywords

discrete timeDoeblin conditionfinite action setsBorel state spacebounded rewardscountable action spacestationary strong 0-discount optimal policies

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items

Bias optimality and strong \(n\) \((n= -1,0)\) discount optimality for Markov decision processes ⋮ Strong \(n\)-discount and finite-horizon optimality for continuous-time Markov decision processes ⋮ Sample-path optimality and variance-maximization for Markov decision processes ⋮ Asymptotic behavior of the value functions of discrete-time discounted optimal control

Cites Work

• Unnamed Item
• Strong 1-optimal stationary policies in denumerable Markov decision processes
• Estimation and control in Markov chains
• Blackwell optimal policies in a Markov decision process with a Borel state space
• Discrete Dynamic Programming
• On Finding Optimal Policies in Discrete Dynamic Programming with No Discounting
• Non-Discounted Denumerable Markovian Decision Models
• Discrete Dynamic Programming with Sensitive Discount Optimality Criteria