Paper published in a book (Scientific congresses and symposiums)
Continuous-state reinforcement learning with fuzzy approximation
Busoniu, Lucian; Ernst, Damien; Babuska, Robert et al.
2007In Proceedings of the 7th European Symposium on Adaptive Learning Agents and Multi-Agent Systems (ALAMAS-07)
Peer reviewed
 

Files


Full Text
alamas-2007.pdf
Publisher postprint (1.1 MB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
reinforcement learning; value iteration; fuzzy approximators
Abstract :
[en] Reinforcement learning (RL) is a widely used learning paradigm for adaptive agents. Well-understood RL algorithms with good convergence and consistency properties exist. In their original form, these algorithms require that the environment states and agent actions take values in a relatively small discrete set. Fuzzy representations for approximate, model-free RL have been proposed in the literature for the more difficult case where the state-action space is continuous. In this work, we propose a fuzzy approximation structure similar to those previously used for Q-learning, but we combine it with the model-based Q-value iteration algorithm. We show that the resulting algorithm converges. We also give a modif ed, serial variant of the algorithm that converges at least as fast as the original version. An illustrative simulation example is provided.
Disciplines :
Computer science
Author, co-author :
Busoniu, Lucian
Ernst, Damien  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Babuska, Robert
De Schutter, Bart
Language :
English
Title :
Continuous-state reinforcement learning with fuzzy approximation
Publication date :
2007
Event name :
7th European Symposium on Adaptive Learning Agents and Multi-Agent Systems (ALAMAS-07)
Event place :
Maastricht, Netherlands
Event date :
2-3 April 2007
Audience :
International
Main work title :
Proceedings of the 7th European Symposium on Adaptive Learning Agents and Multi-Agent Systems (ALAMAS-07)
Pages :
21-35
Peer reviewed :
Peer reviewed
Funders :
F.R.S.-FNRS - Fonds de la Recherche Scientifique
Available on ORBi :
since 29 May 2009

Statistics


Number of views
61 (3 by ULiège)
Number of downloads
177 (2 by ULiège)

Bibliography


Similar publications



Sorry the service is unavailable at the moment. Please try again later.
Contact ORBi