Bounding reward measures of Markov models using the Markov decision processes

DOI10.1002/nla.792zbMath1265.60141OpenAlexW2145769413MaRDI QIDQ4897509

Peter Buchholz

Publication date: 19 December 2012

Published in: Numerical Linear Algebra with Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1002/nla.792

zbMATH Keywords

Markov decision processesMarkov processesboundsstationary analysis

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Bounded-parameter Markov decision processes
• GMRES On (Nearly) Singular Systems
• GMRES: A Generalized Minimal Residual Algorithm for Solving Nonsymmetric Linear Systems
• Bounds for the Positive Eigenvectors of Nonnegative Matrices and for their Approximations by Decomposition
• Bi-CGSTAB: A Fast and Smoothly Converging Variant of Bi-CG for the Solution of Nonsymmetric Linear Systems
• Exact and ordinary lumpability in finite Markov chains
• Computing bounds on steady state availability of repairable computer systems
• Refinable bounds for large Markov chains
• A New Policy Evaluation Algorithm for Markov Decision Processes with Quasi Birth-Death Structure

This page was built for publication: Bounding reward measures of Markov models using the Markov decision processes