Publication detail
Determination of Q-function Optimum Grid for Control Task of Asynchronous Electric Motor
MARADA, T. BŘEZINA, T. SINGULE, V.
Czech title
Stanovení optimálního rastru Q-funkce pro řízení asynchronního elektromotoru
English title
Determination of Q-function Optimum Grid for Control Task of Asynchronous Electric Motor
Type
conference paper
Language
cs
Original abstract
Asynchronous electric motor control task can be successfully solved using reinforcement learning based method called Q-learning. The main problem to solve is the convergence speed. Two-phase Q-learning can be used to speed up the learning process. Efficient prelearning phase uses mathematical model and next phase using for tutorage real system. This method can increase learning speed significantly. When the table is used as Q-function approximation, the learning speed and precision of found controllers depend highly on the Q-function table grid properties. The paper is focused on finding the optimal division of grid.
Czech abstract
Asynchronous electric motor control task can be successfully solved using reinforcement learning based method called Q-learning. The main problem to solve is the convergence speed. Two-phase Q-learning can be used to speed up the learning process. Efficient prelearning phase uses mathematical model and next phase using for tutorage real system. This method can increase learning speed significantly. When the table is used as Q-function approximation, the learning speed and precision of found controllers depend highly on the Q-function table grid properties. The paper is focused on finding the optimal division of grid.
English abstract
Asynchronous electric motor control task can be successfully solved using reinforcement learning based method called Q-learning. The main problem to solve is the convergence speed. Two-phase Q-learning can be used to speed up the learning process. Efficient prelearning phase uses mathematical model and next phase using for tutorage real system. This method can increase learning speed significantly. When the table is used as Q-function approximation, the learning speed and precision of found controllers depend highly on the Q-function table grid properties. The paper is focused on finding the optimal division of grid.
Keywords in English
Asynchronous electromotor, Q-learning, Control, PID
RIV year
2004
Released
24.05.2004
Publisher
Slovak University of Technology Bratislava, Faculty of Mechanical Engineering CA MECHATRONICS
Location
Bratislav, SK
ISBN
80-227-2064-X
Book
Proceedings of the 7th International Symposium "Topical Questions of Teaching Mechatronics"
Journal
Nezařazené články
Pages count
5
BIBTEX
@inproceedings{BUT12316,
author="Tomáš {Marada} and Tomáš {Březina} and Vladislav {Singule},
title="Stanovení optimálního rastru Q-funkce pro řízení asynchronního elektromotoru",
journal="Nezařazené články",
booktitle="Proceedings of the 7th International Symposium "Topical Questions of Teaching Mechatronics"",
year="2004",
month="May",
publisher="Slovak University of Technology Bratislava, Faculty of Mechanical Engineering CA MECHATRONICS",
address="Bratislav, SK",
isbn="80-227-2064-X"
}