Publication detail
Efficient Q-learning modification aplied on active magnetic bearing control
BŘEZINA, T. KREJSA, J.
Czech title
Efficient Q-learning modification aplied on active magnetic bearing control
English title
Efficient Q-learning modification aplied on active magnetic bearing control
Type
journal article - other
Language
en
Original abstract
The paper is focused on use of Q-learning for active magnetic bearing (AMB) control. Q-learning belongs to the reinforcement learning methods which are the part of real time machine learning approaches. The essence of proposed method is in separating the Q-learning into two phases – prelearning phase, which use mathematical model of real system and tutorage phase, which works with the real system and is used for further improvement of Q-values found during the prelearning phase. Proposed learning method, used in prelearning phase, proved to be highly efficient. Controller based on Q-learning show better results (regarding the number of successful trials) than referential PID controller after only 1000 table passes. The control quality criterion results are comparable. The policy found by learning also shows high robustness against errors of system variables observations, even only very simple reinforcement function in shape of simple reduced penalty is used.
Czech abstract
The paper is focused on use of Q-learning for active magnetic bearing (AMB) control. Q-learning belongs to the reinforcement learning methods which are the part of real time machine learning approaches. The essence of proposed method is in separating the Q-learning into two phases – prelearning phase, which use mathematical model of real system and tutorage phase, which works with the real system and is used for further improvement of Q-values found during the prelearning phase. Proposed learning method, used in prelearning phase, proved to be highly efficient. Controller based on Q-learning show better results (regarding the number of successful trials) than referential PID controller after only 1000 table passes. The control quality criterion results are comparable. The policy found by learning also shows high robustness against errors of system variables observations, even only very simple reinforcement function in shape of simple reduced penalty is used.
English abstract
The paper is focused on use of Q-learning for active magnetic bearing (AMB) control. Q-learning belongs to the reinforcement learning methods which are the part of real time machine learning approaches. The essence of proposed method is in separating the Q-learning into two phases – prelearning phase, which use mathematical model of real system and tutorage phase, which works with the real system and is used for further improvement of Q-values found during the prelearning phase. Proposed learning method, used in prelearning phase, proved to be highly efficient. Controller based on Q-learning show better results (regarding the number of successful trials) than referential PID controller after only 1000 table passes. The control quality criterion results are comparable. The policy found by learning also shows high robustness against errors of system variables observations, even only very simple reinforcement function in shape of simple reduced penalty is used.
Keywords in English
Reinforcement learning, Q-learning, Active magnetic bearing
RIV year
2004
Released
01.11.2004
Publisher
Association for engineering mechanics, Czech Republic
ISSN
1210-2717
Journal
Inženýrská mechanika - Engineering Mechanics
Volume
11/2004
Number
2
Pages count
14
BIBTEX
@article{BUT45424,
author="Tomáš {Březina} and Jiří {Krejsa},
title="Efficient Q-learning modification aplied on active magnetic bearing control",
journal="Inženýrská mechanika - Engineering Mechanics",
year="2004",
volume="11/2004",
number="2",
month="November",
publisher="Association for engineering mechanics, Czech Republic",
issn="1210-2717"
}