Přístupnostní navigace
E-application
Search Search Close
Publication result detail
VĚCHET, S., KREJSA, J.
Original Title
Q-Learning: From Discrete to Continuous Representation
English Title
Type
Peer-reviewed article not indexed in WoS or Scopus
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.
English abstract
Keywords
Q-learning, Machine learning, Locally Weighted Regression
Key words in English
Authors
Released
23.08.2004
Location
Warsaw, Poland
ISBN
0033-2089
Periodical
Elektronika
Volume
XVL
Number
8
State
Republic of Poland
Pages from
12
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", pages="3", issn="0033-2089" }