Blackwell optimality in the class of all policies in Markov decision chains with a Borel state space and unbounded rewards

DOI10.1007/S001860050079zbMATH Open0939.90020OpenAlexW1991478799MaRDI QIDQ1974589FDOQ1974589

Authors: Arie Hordijk, Alexander A. Yushkevich 

Publication date: 7 May 2000

Published in: Mathematical Methods of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s001860050079

Recommendations

• Blackwell optimality in the class of stationary policies in Markov decision chains with a Borel state space and unbounded rewards
• Blackwell optimal policies in a Markov decision process with a Borel state space
• Blackwell Optimality in Borelian Continuous-in-Action Markov Decision Processes

zbMATH Keywords

Blackwell optimalityMarkov decision chainsdrift and recurrence conditions

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cited In (14)

• Blackwell optimal policies in a Markov decision process with a Borel state space
• Blackwell optimality in the class of Markov policies for continuous-time controlled Markov chains
• First passage optimality and variance minimisation of Markov decision processes with varying discount factors
• A survey of recent results on continuous-time Markov decision processes (with comments and rejoinder)
• Average, Sensitive and Blackwell Optimal Policies in Denumerable Markov Decision Chains with Unbounded Rewards
• Markov control models with unknown random state-action-dependent discount factors
• Optimality of mixed policies for average continuous-time Markov decision processes with constraints
• Title not available (Why is that?)
• Ergodic Control, Bias, and Sensitive Discount Optimality for Markov Diffusion Processes
• Are limits of \(\alpha\)-discounted optimal policies Blackwell optimal? A counterexample
• Characterization and sufficient conditions for normed ergodicity of Markov chains
• Strong bounds on perturbations
• Average optimality for Markov decision processes in borel spaces: a new condition and approach
• Markov decision processes with state-dependent discount factors and unbounded rewards/costs

This page was built for publication: Blackwell optimality in the class of all policies in Markov decision chains with a Borel state space and unbounded rewards

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1974589)