Learning control of finite Markov chains with unknown transition probabilities

DOI10.1109/TAC.1982.1102893MaRDI QIDQ3950439zbMATH OpenFDO

Authors Mitsuo Sato, H. Takeda, Kenichi Abe

Publication date 1982

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

Full work available at URL https://doi.org/10.1109/TAC.1982.1102893

zbMATH Keywords

asymptotic optimalitylearning algorithmsMarkovian decision problem

Mathematics Subject Classification ID

Bayesian problems; characterization of Bayes procedures (62C10) Markov processes: estimation; hidden Markov models (62M05) Optimal stochastic control (93E20)

Cited in

(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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3950439)