Efficient learning of reactive robot behaviors with a Neural-Q_learning approach
dc.contributor.author
dc.date.accessioned
2010-05-05T11:38:43Z
dc.date.available
2010-05-03T15:06:24Z
2010-05-05T11:38:43Z
dc.date.issued
2002
dc.identifier.citation
Carreras, M., Ridao, P. , Batlle, J., i Nicosevici, T. (2002). Efficient learning of reactive robot behaviors with a Neural-Q_learning approach. IEEE/RSJ International Conference on Intelligent Robots and Systems, 1, 1020-1025. Recuperat 05 maig 2010, a http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1041525
dc.identifier.isbn
0-7803-7398-7
dc.identifier.uri
dc.description.abstract
The purpose of this paper is to propose a Neural-Q_learning approach designed for online learning of simple and reactive robot behaviors. In this approach, the Q_function is generalized by a multi-layer neural network allowing the use of continuous states and actions. The algorithm uses a database of the most recent learning samples to accelerate and guarantee the convergence. Each Neural-Q_learning function represents an independent, reactive and adaptive behavior which maps sensorial states to robot control actions. A group of these behaviors constitutes a reactive control scheme designed to fulfill simple missions. The paper centers on the description of the Neural-Q_learning based behaviors showing their performance with an underwater robot in a target following task. Real experiments demonstrate the convergence and stability of the learning system, pointing out its suitability for online robot learning. Advantages and limitations are discussed
dc.format.mimetype
application/pdf
dc.language.iso
eng
dc.publisher
IEEE
dc.relation.isformatof
Reproducció digital del document publicat a: http://dx.doi.org/10.1109/IRDS.2002.1041525
dc.relation.ispartof
© IEEE/RSJ International Conference on Intelligent Robots and Systems, 2002, vol. 1, p. 1020-1025
dc.relation.ispartofseries
Articles publicats (D-ATC)
dc.rights
Tots els drets reservats
dc.subject
dc.title
Efficient learning of reactive robot behaviors with a Neural-Q_learning approach
dc.type
info:eu-repo/semantics/article
dc.rights.accessRights
info:eu-repo/semantics/openAccess
dc.identifier.doi