Neural Symbolic Architecture for Normative Agents

Reference : Neural Symbolic Architecture for Normative Agents


	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/10993/12973

Title :	Neural Symbolic Architecture for Normative Agents
Language :	English
Author, co-author :	Boella, Guido []
	Colombo Tosatto, Silvano []
	d'Avila Garcez, Artur []
	Genovese, Valerio []
	Ienco, Dino []
	van der Torre, Leon [University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) >]
Publication date :	2011
Main document title :	In Proceedings of The Seventh International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2011). May, 2011
Peer reviewed :	Yes
Audience :	International
ISBN :	0-9826571-7-X 978-0-9826571-7-1
Event name :	Artificial Agents and Multi-Agents Systems 2011
Event date :	May 2-6 2011
Keywords :	[en] neural-symbolic architecture ; multi-agent systems
Abstract :	[en] In this paper we propose a neural-symbolic architecture to represent and reason with norms in multi-agent systems. On the one hand, the architecture contains a symbolic knowledge base to represent norms and on the other hand it contains a neural network to reason with norms. The interaction between the symbolic knowledge and the neural network is used to learn norms. We describe how to handle normative reasoning issues like contrary to duties, dilemmas and exceptions by using a priority-based ordering between the norms in a neural-symbolic architecture.
Target :	Researchers ; Professionals ; Students ; General public ; Others
Permalink :	http://hdl.handle.net/10993/12973
Other URL :	http://dl.acm.org/citation.cfm?id=2034488

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	aamas2011_Neural.pdf		Publisher postprint	412.25 kB	View/Open

All documents in ORBi^lu are protected by a user license.