Optimality equations and sensitive optimality in bounded Markov decision processes1

DOI10.1080/02331938508843074zbMath0587.90099OpenAlexW2118289446MaRDI QIDQ3714928

Elke Mann

Publication date: 1985

Published in: Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/02331938508843074

zbMATH Keywords

average reward criterioncountable state spaceoptimal stationary policiesoptimality equationsdiscrete time Markov decision processbounded reward functionsensitive optimality criteriacompact sets of admissible actions

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Related Items (4)

Simultaneous recurrent conditions on countable state Markov chains ⋮ Notes on variance in randomized reward Markov decision processes ⋮ Denumerable semi-Markov decision chains with small interest rates ⋮ Estimation and control in multichain processes

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Denumerable Undiscounted Semi-Markov Decision Processes with Unbounded Rewards
• Continuity of mean recurrence times in denumerable semi-Markov processes
• Average, Sensitive and Blackwell Optimal Policies in Denumerable Markov Decision Chains with Unbounded Rewards
• The Functional Equations of Undiscounted Markov Renewal Programming
• Discrete Dynamic Programming
• On Finding Optimal Policies in Discrete Dynamic Programming with No Discounting
• Discrete Dynamic Programming with Sensitive Discount Optimality Criteria
• Perturbation theory and finite Markov chains
• Multichain Markov Renewal Programs

This page was built for publication: Optimality equations and sensitive optimality in bounded Markov decision processes¹