Publication detail

Q-Learning: From Discrete to Continuous Representation

VĚCHET, S. KREJSA, J.

Czech title

Modifikace metody Q-učení z diskrétní na spojitou

English title

Q-Learning: From Discrete to Continuous Representation

Type

journal article - other

Language

en

Original abstract

Q-learning standard algorithm is restricted by using discrete states and actions. In this case Q-function is usually represented as a discrete table of Q-values. Conversion of continuous variables to adequate discrete variables evokes some problems. Problems can be avoided if the continuous algorithm of Q-learning is used. In this paper we discus method, which is used to convert discrete to continuous algorithm. The method used suitable approximator to replace the discrete table. We choose local approximator called Locally Weighted Regression (LWR) (Atketson &Moore & Shaal, 1996) from the group of memory based approximators.

Czech abstract

Tento článek pojednává o způsobu převedení standardní metody Q-učení, která je pouze diskrétní, na spojitou. K tomuto účelu je použit jednoduchý lokální aproximátor Lokálně vážená regrese (LVR). Tento aproximátor slouží k převedení diskrétní tabulky Q-hodnot na spojitou Q-funkci.

English abstract

Q-learning standard algorithm is restricted by using discrete states and actions. In this case Q-function is usually represented as a discrete table of Q-values. Conversion of continuous variables to adequate discrete variables evokes some problems. Problems can be avoided if the continuous algorithm of Q-learning is used. In this paper we discus method, which is used to convert discrete to continuous algorithm. The method used suitable approximator to replace the discrete table. We choose local approximator called Locally Weighted Regression (LWR) (Atketson &Moore & Shaal, 1996) from the group of memory based approximators.

Keywords in English

Q-learning, Machine learning, Locally Weighted Regression

RIV year

2004

Released

23.08.2004

Location

Warsaw, Poland

ISSN

0033-2089

Journal

Elektronika

Volume

XVL

Number

8

Pages count

3

BIBTEX


@article{BUT42197,
  author="Stanislav {Věchet} and Jiří {Krejsa},
  title="Q-Learning: From Discrete to Continuous Representation",
  journal="Elektronika",
  year="2004",
  volume="XVL",
  number="8",
  month="August",
  address="Warsaw, Poland",
  issn="0033-2089"
}