A class of procedures to compute the optimal value f unction in a Markovian decision problem

DOI10.1080/02331938608843148zbMath0594.90091OpenAlexW1989482537MaRDI QIDQ3725896

Jörg-Uwe Löbus

Publication date: 1986

Published in: Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/02331938608843148

zbMATH Keywords

successive approximation methodfinite state Markov decision processeseffective computation of the value functionfinite expected discounted or non- discounted rewardsimproving the convergence rate

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cites Work

• Unnamed Item
• Unnamed Item

This page was built for publication: A class of procedures to compute the optimal value f unction in a Markovian decision problem