Detail publikace

Q-Learning: From Discrete to Continuous Representation

VĚCHET, S. KREJSA, J.

Anglický název

Q-Learning: From Discrete to Continuous Representation

Typ

Článek recenzovaný mimo WoS a Scopus

Jazyk

en

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.

Klíčová slova anglicky

Q-learning, Machine learning, Locally Weighted Regression

Vydáno

2004-08-23

Místo

Warsaw, Poland

ISSN

0033-2089

Časopis

Elektronika

Ročník

XVL

Číslo

8

Strany od–do

12–

Počet stran

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"
}