Detail publikace
Q-LEARNING USED FOR CONTROL OF AMB: REDUCED STATE DEFINITION
BŘEZINA, T. KREJSA, J.
Anglický název
Q-LEARNING USED FOR CONTROL OF AMB: REDUCED STATE DEFINITION
Typ
Stať ve sborníku v databázi WoS či Scopus
Jazyk
en
Originální abstrakt
A great intention is lately focused on Reinforcement Learning (RL) methods. Previous work showed that stochastic strategy improved model free RL method known as Q-learning used on active magnetic bearing (AMB) model. So far the position, velocity and acceleration were used to describe the state of the system. This paper shows simplified version of controller which uses reduced state definition – position and velocity only. Furthermore the controlled initial conditions area and its development during learning are shown. Numerical experiments proved that simplified controller version is fully capable of AMB control.
Klíčová slova anglicky
Reinforcement Learning, Q-learning, Active Magnetic Bearing
Vydáno
2002-06-05
Nakladatel
Brno University of Technology, Faculty of Mechanical Engineering
Místo
Brno
ISBN
80-214-2135-5
Kniha
Mendel 2002
Strany od–do
347–
Počet stran
6
BIBTEX
@inproceedings{BUT10054,
author="Tomáš {Březina} and Jiří {Krejsa}",
title="Q-LEARNING USED FOR CONTROL OF AMB: REDUCED STATE DEFINITION",
booktitle="Mendel 2002",
year="2002",
number="1",
pages="6",
publisher="Brno University of Technology, Faculty of Mechanical Engineering",
address="Brno",
isbn="80-214-2135-5"
}