Detail publikace

Reinforcement learning model: control of nonlinear and unstable processes

BŘEZINA, T. EHRENBERGER, Z. KRATOCHVÍL, C.

Anglický název

Reinforcement learning model: control of nonlinear and unstable processes

Typ

Stať ve sborníku v databázi WoS či Scopus

Jazyk

en

Originální abstrakt

Some experiences with using of the reinforcement learning model at control of nonlinear unstable processes are published in this paper. Control process is characterized by extensive depth in such cases, so the learning is computationally very demanding. We propose both using of nonlinear grid of the Q-function approximation table and also using of the learning conception “by expert observation“. Learning off (optimal) control policy is not based on blind searching a state space, but it is in progress with the help of further component, that is able to control the process. Problems are studied on active magnetic bearing one-mass model.

Klíčová slova anglicky

control algorithm, Q-learning, neural network

Vydáno

2001-06-14

Nakladatel

Institute of Termomechanics Academy of Sience of the Czech Republic, Prague 2001

Místo

Svratka

ISBN

80-85918-64-1

Kniha

Inženýrská Mechanika 2001

Strany od–do

40–

Počet stran

2

BIBTEX


@inproceedings{BUT6259,
  author="Tomáš {Březina} and Zdeněk {Ehrenberger} and Ctirad {Kratochvíl}",
  title="Reinforcement learning model: control of nonlinear and unstable processes",
  booktitle="Inženýrská Mechanika 2001",
  year="2001",
  number="1",
  pages="2",
  publisher="Institute of Termomechanics
Academy of Sience of the Czech Republic,
Prague 2001",
  address="Svratka",
  isbn="80-85918-64-1"
}