Detail publikace
STOCHASTIC POLICY IN Q-LEARNING USED FOR CONTROL OF AMB
BŘEZINA, T. KREJSA, J. VĚCHET, S.
Český název
STOCHASTIC POLICY IN Q-LEARNING USED FOR CONTROL OF AMB
Anglický název
STOCHASTIC POLICY IN Q-LEARNING USED FOR CONTROL OF AMB
Typ
Stať ve sborníku v databázi WoS či Scopus
Jazyk
cs
Originální abstrakt
A great intention is lately focused on Reinforcement Learning (RL) methods. The article is focused on improving model free RL method known as Q-learning algorithm used on active magnetic bearing (AMB) model. Stochastic strategy and adaptive integration step increased the speed of learning approximately hundred times. Impossibility of using proposed improvement online is the only drawback, however it might be used for pretraining on simulation model and further fined online.
Anglický abstrakt
A great intention is lately focused on Reinforcement Learning (RL) methods. The article is focused on improving model free RL method known as Q-learning algorithm used on active magnetic bearing (AMB) model. Stochastic strategy and adaptive integration step increased the speed of learning approximately hundred times. Impossibility of using proposed improvement online is the only drawback, however it might be used for pretraining on simulation model and further fined online.
Klíčová slova česky
Reinforcement Learning, Q-learning, Active Magnetic Bearing
Klíčová slova anglicky
Reinforcement Learning, Q-learning, Active Magnetic Bearing
Vydáno
2002-05-13
Nakladatel
Institute of Mechanics of Solids, Faculty of Mechanical Engineering, Brno University of Technology
Místo
Brno
ISBN
80-214-2109-6
Kniha
Inženýrská mechanika 2002
Strany od–do
7–
Počet stran
2
BIBTEX
@inproceedings{BUT9663,
author="Tomáš {Březina} and Jiří {Krejsa} and Stanislav {Věchet}",
title="STOCHASTIC POLICY IN Q-LEARNING USED FOR CONTROL OF AMB",
booktitle="Inženýrská mechanika 2002",
year="2002",
number="1",
pages="2",
publisher="Institute of Mechanics of Solids, Faculty of Mechanical Engineering, Brno University of Technology",
address="Brno",
isbn="80-214-2109-6"
}