Přístupnostní navigace
E-application
Search Search Close
Publication detail
VĚCHET, S., KREJSA, J.
Original Title
Continuous Q-learning application
Type
conference paper
Language
English
Original Abstract
Standard algorithm of Q-Learning is limited by discrete states and actions and Q-function is usually represented as discrete table. To avoid this obstacle and extend the use of Q-learning for continuous states and actions the algorithm must be modified and such modification is presented in the paper. Straightforward way is to replace discrete table with suitable approximator. A number of approximators can be used, with respect to memory and computational requirements the local approximator is particularly favorable. We have used Locally Weighted Regression (LWR) algorithm. The paper discusses advantages and disadvantages of modified algorithm demonstrated on simple control task.
Keywords
Q-learning, Machine learning, Locall approximators
Authors
RIV year
2004
Released
10. 5. 2004
Publisher
Institute of Thermonechanics Academy of Sciences of the Czech Republic, Prague 2004
Location
Prague
ISBN
80-85918-88-9
Book
Engineering Mechanics 2004
Edition number
1
Pages from
307
Pages to
308
Pages count
2
BibTex
@inproceedings{BUT14018, author="Stanislav {Věchet} and Jiří {Krejsa}", title="Continuous Q-learning application", booktitle="Engineering Mechanics 2004", year="2004", number="1", pages="2", publisher="Institute of Thermonechanics Academy of Sciences of the Czech Republic, Prague 2004", address="Prague", isbn="80-85918-88-9" }