Engineering Mechanics

Proceedings Vol. 7 (2001)

INŽENÝRSKÁ MECHANIKA 2001

ENGINEERING MECHANICS 2001

NATIONAL CONFERENCE WITH INTERNATIONAL PARTICIPATION
May 14 – 17, 2001, Svratka, Czech Republic

;

Editors: Alena Poživilová and Jan Masák

ISBN 80-885918-64-1 (printed)
ISSN 1805-8248 (printed)
ISSN 1805-8256 (electronic)

list of papers scientific commitee

Reinforcement learning model: control of nonlinear and unstable processes

Březina T., Ehrenberger Z., Kratochvíl C.
pages 40 - +8p, full text

Some experiences with using of the reinforcement learning model at control of non linear unstable processes are published in this paper. Control process is characterized by extensive depth in such cases. so the learning is computationaliy very demanding. We propose both using of non linear 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.

back to list of papers

Text and facts may be copied and used freely, but credit should be given to these Proceedings.

All papers were reviewed by members of the scientific committee.

Engineering Mechanics

International Conference

Proceedings Vol. 7 (2001)

INŽENÝRSKÁ MECHANIKA 2001

ENGINEERING MECHANICS 2001