A selection algorithm for ∊-optimal policies in undiscounted maekovian decision problems

DOI10.1080/02331938108842739MaRDI QIDQ3661345zbMATH OpenOpenAlexWikidataFDO

Authors S. Glogner, A. Hahnewald-Busch

Publication date 1981

Published in Mathematische Operationsforschung und Statistik. Series Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/02331938108842739

zbMATH Keywords

algorithmdisjoint decomposition of the policy setepsilon- optimal policyfinite-state, finite- action undiscounted Markovian decision problemHoward's policy iterationwhole set of optimal or epsilon-optimal policies

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

This page was built for publication: A selection algorithm for ∊-optimal policies in undiscounted maekovian decision problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3661345)