Detail publikace
Asynchronous electromotor controller tuned hrough CARLA method
BŘEZINA, T. TUREK, M.
Český název
Asynchronous electromotor controller tuned hrough CARLA method
Anglický název
Asynchronous electromotor controller tuned hrough CARLA method
Typ
článek v časopise - ostatní, Jost
Jazyk
en
Originální abstrakt
Relatively unknown reinforcement learning algorithm, so called continuous action reinforcement learning automaton, is presented in this contribution. Automaton learning algorithm is based on rewarding, that gradually evolves set of probability densities. This set is consequently used for action set determination. Simulation study describing learning and behavior of asynchronous electromotor control is further presented. Standard PSD controller is used whose parameter values represent actions of three independent automata. The aim of online learning process is to minimize mean square of control error. Here described learning algorithm is simple to implement and robust to high level of noise.
Český abstrakt
Relatively unknown reinforcement learning algorithm, so called continuous action reinforcement learning automaton, is presented in this contribution. Automaton learning algorithm is based on rewarding, that gradually evolves set of probability densities. This set is consequently used for action set determination. Simulation study describing learning and behavior of asynchronous electromotor control is further presented. Standard PSD controller is used whose parameter values represent actions of three independent automata. The aim of online learning process is to minimize mean square of control error. Here described learning algorithm is simple to implement and robust to high level of noise.
Anglický abstrakt
Relatively unknown reinforcement learning algorithm, so called continuous action reinforcement learning automaton, is presented in this contribution. Automaton learning algorithm is based on rewarding, that gradually evolves set of probability densities. This set is consequently used for action set determination. Simulation study describing learning and behavior of asynchronous electromotor control is further presented. Standard PSD controller is used whose parameter values represent actions of three independent automata. The aim of online learning process is to minimize mean square of control error. Here described learning algorithm is simple to implement and robust to high level of noise.
Klíčová slova anglicky
Asynchronous electromotor, CARLA, Control
Rok RIV
2004
Vydáno
23.09.2004
Nakladatel
Warsaw University of Technology, Faculty of Mechatronics
Místo
Warsaw, Poland
ISSN
0033-2089
Časopis
Elektronika
Ročník
2004
Číslo
8-9
Počet stran
4
BIBTEX
@article{BUT45422,
author="Tomáš {Březina} and Milan {Turek},
title="Asynchronous electromotor controller tuned hrough CARLA method",
journal="Elektronika",
year="2004",
volume="2004",
number="8-9",
month="September",
publisher="Warsaw University of Technology, Faculty of Mechatronics",
address="Warsaw, Poland",
issn="0033-2089"
}