Show simple item record

dc.contributor.authorCranefield, Stephen
dc.contributor.authorMeneguzzi, Felipe
dc.contributor.authorOren, Nir
dc.contributor.authorSavarimuthu, Bastin Tony Roy
dc.date.available2015-02-24T22:12:55Z
dc.date.copyright2015
dc.identifier.citationCranefield, S., Meneguzzi, F., Oren, N., & Savarimuthu, B. T. R. (2015). A Bayesian approach to norm identification (Technical Report). Retrieved from http://hdl.handle.net/10523/5476en
dc.identifier.urihttp://hdl.handle.net/10523/5476
dc.description.abstractWhen entering a system, an agent should be aware of the obligations and prohibitions (collectively norms) that will affect it. Existing solutions to this norm identification problem make use of observations of either other's norm compliant, or norm violating, behaviour. However, they assume an extreme situation where norms are typically violated, or complied with. In this paper we propose a Bayesian approach to norm identification which operates by learning from both norm compliant and norm violating behaviour. By utilising both types of behaviour, we not only overcome a major limitation of existing approaches, but also obtain improved performance over the state-of-the-art, allowing norms to be learned with a few observations. We evaluate the effectiveness of this approach empirically and discuss theoretical limitations to its accuracy.en_NZ
dc.format.mimetypeapplication/pdf
dc.language.isoenen_NZ
dc.titleA Bayesian approach to norm identificationen_NZ
dc.typeTechnical Report
dc.date.updated2015-02-24T03:53:30Z
otago.schoolInformation Scienceen_NZ
otago.openaccessOpen
 Find in your library

Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record