Publication detail
Use of continous action reinforcement learning automata for asynchronous electromotro control
BŘEZINA, T. TUREK, M.
Czech title
Use of continous action reinforcement learning automata for asynchronous electromotro control
English title
Use of continous action reinforcement learning automata for asynchronous electromotro control
Type
conference paper
Language
cs
Original abstract
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, robust to high level of noise.
Czech abstract
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, robust to high level of noise.
English abstract
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, robust to high level of noise.
Keywords in Czech
Asynchronous electromotor, CARLA, PSD Controller, Control
Keywords in English
Asynchronous electromotor, CARLA, PSD Controller, Control
RIV year
2004
Released
10.05.2004
Publisher
Institute of Thermomechanics, Academy of Sciences of the Czec Republic
Location
Svratka
ISBN
80-85918-88-9
Book
Enigneering Mechanics 2004, National Conference with International Participation
Pages count
2
BIBTEX
@inproceedings{BUT12457,
author="Tomáš {Březina} and Milan {Turek},
title="Use of continous action reinforcement learning automata for asynchronous electromotro control",
booktitle="Enigneering Mechanics 2004, National Conference with International Participation",
year="2004",
month="May",
publisher="Institute of Thermomechanics, Academy of Sciences of the Czec Republic",
address="Svratka",
isbn="80-85918-88-9"
}