Detail publikačního výsledku

Q-Learning: From Discrete to Continuous Representation

VĚCHET, S., KREJSA, J.

Originální název

Q-Learning: From Discrete to Continuous Representation

Anglický název

Q-Learning: From Discrete to Continuous Representation

Druh

Článek recenzovaný mimo WoS a Scopus

Originální abstrakt

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.

Anglický abstrakt

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.

Klíčová slova

Q-learning, Machine learning, Locally Weighted Regression

Klíčová slova v angličtině

Q-learning, Machine learning, Locally Weighted Regression

Autoři

VĚCHET, S., KREJSA, J.

Vydáno

23.08.2004

Místo

Warsaw, Poland

ISSN

0033-2089

Periodikum

Elektronika

Svazek

XVL

Číslo

8

Stát

Polská republika

Strany od

12

Strany počet

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",
  pages="3",
  issn="0033-2089"
}