A reinforcement learning approach based on the fuzzy min-max neural network

 
This item is provided by the institution :

Repository :
Digital Library of National Technical University of Athens | Dspace@NTUA
see the original item page
in the repository's web site and access all digital files if the item*
share



Semantic enrichment by EKT
Journal part (EN)
Scientific article (EN)
1996 (EN)
A reinforcement learning approach based on the fuzzy min-max neural network (EN)
Likas, A (EN)
Blekas, K (EN)
The fuzzy min-max neural network constitutes a neural architecture that is based on hyperbox fuzzy sets and can be incrementally trained by appropriately adjusting the number of hyperboxes and their corresponding volumes. Two versions have been proposed: for supervised and unsupervised learning. In this paper a modified approach is presented that is appropriate for reinforcement learning problems with discrete action space and is applied to the difficult task of autonomous vehicle navigation when no a priori knowledge of the enivronment is available. Experimental results indicate that the proposed reinforcement learning network exhibits superior learning behavior compared to conventional reinforcement schemes. © 1996 Kluwer Academic Publishers. (EN)
journalArticle (EN)
Learning systems (EN)
Autonomous vehicle navigation (EN)
Fuzzy sets (EN)
Neurosciences (EN)
Navigation (EN)
Fuzzy min max neural networks (EN)
Neural networks (EN)
Fuzzy min-max neural network (EN)
Reinforcement learning (EN)
Computer Science, Artificial Intelligence (EN)
Robots (EN)
National Technical University of Athens
Digital Library of National Technical University of Athens | Dspace@NTUA
Κεντρική Βιβλιοθήκη Ε.Μ.Π.
Ιδρυματικό Αποθετήριο
Δημοσιεύσεις μελών Δ.Ε.Π. σε περιοδικά
Neural Processing Letters (EN)
English
1996 (EN)
http://hdl.handle.net/123456789/11744
167 (EN)
3 (EN)
1370-4621 (EN)
4 (EN)
ISI:A1996WN61100006 (EN)
172 (EN)
KLUWER ACADEMIC PUBL (EN)



*Institutions are responsible for keeping their URLs functional (digital file, item page in repository site)