Publication detail

Reinforcement learning model: control of nonlinear and unstable processes

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

Original Title

Reinforcement learning model: control of nonlinear and unstable processes

Type

conference paper

Language

English

Original Abstract

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.

Keywords

control algorithm, Q-learning, neural network

Authors

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

RIV year

2002

Released

14. 6. 2001

Publisher

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

Location

Svratka

ISBN

80-85918-64-1

Book

Inženýrská Mechanika 2001

Edition number

1

Pages from

40

Pages to

41

Pages count

2

BibTex

@{BUT69519
}