Adding Reinforcement Learning Features to the Neural-Gas Method

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by M. Winter Articles by G. Metta Articles by G. Sandini

IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 4

Como, Italy

July 24-July 27

ISBN: 0-7695-0619-4

	ASCII Text	x
	M. Winter, G. Metta, G. Sandini, "Adding Reinforcement Learning Features to the Neural-Gas Method," Neural Networks, IEEE - INNS - ENNS International Joint Conference on, vol. 4, pp. 4539, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 4, 2000.

	BibTex	x
	@article{ 10.1109/IJCNN.2000.860827, author = {M. Winter and G. Metta and G. Sandini}, title = {Adding Reinforcement Learning Features to the Neural-Gas Method}, journal ={Neural Networks, IEEE - INNS - ENNS International Joint Conference on}, volume = {4}, year = {2000}, issn = {1098-7576}, pages = {4539}, doi = {http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.860827}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Neural Networks, IEEE - INNS - ENNS International Joint Conference on TI - Adding Reinforcement Learning Features to the Neural-Gas Method SN - 1098-7576 SP EP A1 - M. Winter, A1 - G. Metta, A1 - G. Sandini, PY - 2000 VL - 4 JA - Neural Networks, IEEE - INNS - ENNS International Joint Conference on ER -

M. Winter, University of Genoa

G. Metta, University of Genoa

G. Sandini, University of Genoa

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.860827

We propose a new neural approach for approximating function using reinforcement-type learning: each time the network generates an output, the environment responds with the scalar distance between the delivered output and the expected one. Thus, this distance is the only information the network can use to modify the estimation of the multi-dimensional output. This reinforcement feature is embedded in a neural-gas method, taking advantages of the different facilities it offers. We detail the global algorithm and we present some simulation results in order to show the behavior of the developed method.

Citation:

M. Winter, G. Metta, G. Sandini, "Adding Reinforcement Learning Features to the Neural-Gas Method," ijcnn, vol. 4, pp.4539, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 4, 2000

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.