Learning control of finite Markov chains with unknown transition probabilities

From MaRDI portal

Revision as of 23:18, 5 February 2024 by Import240129110113 (talk | contribs) (Created automatically from import240129110113)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Publication:3950439

Jump to:navigation, search

DOI10.1109/TAC.1982.1102893zbMath0488.93070MaRDI QIDQ3950439

Mitsuo Sato, Hiroshi Takeda, Ken-Ichi Abe

Publication date: 1982

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

zbMATH Keywords

learning algorithms asymptotic optimality Markovian decision problem

Mathematics Subject Classification ID

Lua error in Module:PublicationMSCList at line 37: attempt to index local 'msc_result' (a nil value).

Related Items (1)

An incremental off-policy search in a model-free Markov decision process using a single sample path

This page was built for publication: Learning control of finite Markov chains with unknown transition probabilities

Retrieved from "https://portal.mardi4nfdi.de/w/index.php?title=Publication:3950439&oldid=17645479"

Pages with script errors