Semi-infinite discounted Markov decision processes: Policy improvement and singular perturbations

DOI10.1007/S001860100143MaRDI QIDQ1397012zbMATH OpenOpenAlexFDO

Authors Mohammed Abbad, Khalid Rahhali

Publication date 16 July 2003

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

Full work available at URL https://doi.org/10.1007/s001860100143

zbMATH Keywords

Markov decision

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Time-scale analysis and singular perturbations in control/observation systems (93C70)

Recommendations

• Asymptotic linear programming and policy improvement for singularly perturbed Markov decision processes
• Semi-infinite Markov decision processes
• Algorithms for singularly perturbed limiting average Markov control problems
• Nearly optimal control of singularly perturbed Markov decision processes in discrete time
• Singularly perturbed discounted Markov control processes in a general state space

Cited in

(2)

• Semi-infinite weighted Markov decision processes with perturbation.
• Semi-Infinite Weighted Markov Decision Processes

This page was built for publication: Semi-infinite discounted Markov decision processes: Policy improvement and singular perturbations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1397012)