Reference : Learning and Reasoning about Norms using Neural-Symbolic Systems
Scientific congresses, symposiums and conference proceedings : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/10993/12975
Learning and Reasoning about Norms using Neural-Symbolic Systems
English
Perotti, Alan [University of Torino, Italy]
Boella, Guido [University of Torino, Italy]
Colombo Tosatto, Silvano mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
d’Avila Garcez, Artur S. [City University London, England]
Genovese, Valerio [University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) >]
van der Torre, Leon mailto [University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) >]
2012
International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2012, Valencia, Spain, June 4-8, 2012
1023-1030
Yes
International
978-0-9817381-2-3
AAMAS 12 International Conference on Autonomous Agents and Multiagent Systems
June 04 - 08, 2012
Valencia
Spain
[en] Knowledge representation ; Single agent reasoning ; Computational architectures for learning ; Single agent learning
[en] In this paper we provide a neural-symbolic framework to model, reason about and learn norms in multi-agent systems. To this purpose, we define a fragment of Input/Output (I/O) logic that can be embedded into a neural network. We extend d’Avila Garcez et al. Connectionist Inductive Learning and Logic Programming System (CILP) to translate an I/O logic theory into a Neural Network (NN) that can be trained further with examples: we call this new system Normative- CILP (N-CILP). We then present a new algorithm to handle priorities between rules in order to cope with normative issues like Contrary to Duty (CTD), Priorities, Exceptions and Permissions. We illustrate the applicability of the framework on a case study based on RoboCup rules: within this working example, we compare the learning capacity of a network built with N-CILP with a non symbolic neural net- work, we explore how the initial knowledge impacts on the overall performance, and we test the NN capacity of learn- ing norms, generalizing new Contrary to Duty rules from examples.
Researchers ; Professionals ; Students ; General public ; Others
http://hdl.handle.net/10993/12975
http://dl.acm.org/citation.cfm?id=2343843
2
Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems - Volume 2

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
2F_3.pdfNo commentaryAuthor postprint1.15 MBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.