Publication detail

Effect of Table Grid at Q-learning Process of Active Magnetic Bearing Controller

BŘEZINA, T.

English title

Effect of Table Grid at Q-learning Process of Active Magnetic Bearing Controller

Type

conference paper

Language

en

Original abstract

Paper describes numerical experiments when Q-learning with implemented table grid is applied to the active magnetic bearing controller. The aim is to find the smallest grid of table of Q-learning architecture, which provide sufficient control of magnetic bearing. There are used linear and also nonlinear grids of the table. A simple single-mass model of the magnetic bearing is used. Q-learning using found values of the table was proved especially from a speed point of view. Presumably further experiment will lead to table improving learning process.

English abstract

Paper describes numerical experiments when Q-learning with implemented table grid is applied to the active magnetic bearing controller. The aim is to find the smallest grid of table of Q-learning architecture, which provide sufficient control of magnetic bearing. There are used linear and also nonlinear grids of the table. A simple single-mass model of the magnetic bearing is used. Q-learning using found values of the table was proved especially from a speed point of view. Presumably further experiment will lead to table improving learning process.

Keywords in English

Q-learning, magnetic bearing controller, magnetic bearing

RIV year

2001

Released

06.06.2001

Location

Brno, ČR

ISBN

80-214-1894-X

Book

Mendel 2001

Pages count

6

BIBTEX


@inproceedings{BUT6256,
  author="Tomáš {Březina},
  title="Effect of Table Grid at Q-learning Process of Active Magnetic Bearing Controller",
  booktitle="Mendel 2001",
  year="2001",
  month="June",
  address="Brno, ČR",
  isbn="80-214-1894-X"
}