Detail publikace

Determination of Q-function optimum grid applied on asynchronous electric motor control task

MARADA, T., BŘEZINA, T., SINGULE, V.

Originální název

Determination of Q-function optimum grid applied on asynchronous electric motor control task

Český název

Determination of Q-function optimum grid applied on asynchronous electric motor control task

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

cs

Originální abstrakt

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.

Český abstrakt

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.

Klíčová slova

Asynchronous electric motor, Q-learning, control

Rok RIV

2004

Vydáno

10.05.2004

Nakladatel

Institute of Thermomechanics, Academy of Sciences of the Czec Republic

Místo

Svratka

ISBN

80-85918-88-9

Kniha

Enigneering Mechanics 2004, National Conference with International Participation

Strany od

177

Strany do

178

Strany počet

2

BibTex


@inproceedings{BUT12317,
  author="Tomáš {Marada} and Tomáš {Březina} and Vladislav {Singule}",
  title="Determination of Q-function optimum grid applied on asynchronous electric motor control task",
  annote="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.",
  address="Institute of Thermomechanics, Academy of Sciences of the Czec Republic",
  booktitle="Enigneering Mechanics 2004, National Conference with International Participation",
  chapter="12317",
  institution="Institute of Thermomechanics, Academy of Sciences of the Czec Republic",
  journal="Nezařazené články",
  year="2004",
  month="may",
  pages="177",
  publisher="Institute of Thermomechanics, Academy of Sciences of the Czec Republic",
  type="conference paper"
}