English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/96699
Share/Impact:
Statistics
logo share SHARE   Add this article to your Mendeley library MendeleyBASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar a otros formatos:
Title

A competitive strategy for function approximation in Q-learning

AuthorsAgostini, Alejandro ; Celaya, Enric
Issue Date2011
PublisherAAAI Press
CitationInternational Joint Conference on Artificial Intelligence 2: 1146-1151 (2011)
AbstractIn this work we propose an approach for generalization in continuous domain Reinforcement Learning that, instead of using a single function approximator, tries many different function approximators in parallel, each one defined in a different region of the domain. Associated with each approximator is a relevance function that locally quantifies the quality of its approximation, so that, at each input point, the approximator with highest relevance can be selected. The relevance function is defined using parametric estimations of the variance of the q-values and the density of samples in the input space, which are used to quantify the accuracy and the confidence in the approximation, respectively. These parametric estimations are obtained from a probability density distribution represented as a Gaussian Mixture Model embedded in the input-output space of each approximator. In our experiments, the proposed approach required a lesser number of experiences for learning and produced more stable convergence profiles than when using a single function approximator.
DescriptionTrabajo presentado al 22nd IJCAI celebrado en Barcelona del 16 al 22 de julio de 2011.
Publisher version (URL)http://ijcai.org/papers11/contents.php
URIhttp://hdl.handle.net/10261/96699
Identifiersisbn: 978-1-57735-514-4
Appears in Collections:(IRII) Libros y partes de libros
Files in This Item:
File Description SizeFormat 
A competitive strategy.pdf335,34 kBUnknownView/Open
Show full item record
Review this work
 


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.