Show simple item record

dc.contributor.authorRIVERET, Regis
dc.contributor.authorGAO, Yang
dc.contributor.authorGOVERNATORI, Guido
dc.contributor.authorROTOLO, Antonino
dc.contributor.authorPITT, Jeremy
dc.contributor.authorSARTOR, Giovanni
dc.date.accessioned2020-02-10T16:08:54Z
dc.date.available2020-02-10T16:08:54Z
dc.date.issued2019
dc.identifier.citationAutonomous agents and multi-agent systems, 2019, Vol. 33, No. 1-2, pp. 216-274en
dc.identifier.issn1387-2532
dc.identifier.issn1573-7454
dc.identifier.urihttps://hdl.handle.net/1814/66098
dc.descriptionPublished March 2019 en
dc.description.abstractA bounded-reasoning agent may face two dimensions of uncertainty: firstly, the uncertainty arising from partial information and conflicting reasons, and secondly, the uncertainty arising from the stochastic nature of its actions and the environment. This paper attempts to address both dimensions within a single unified framework, by bringing together probabilistic argumentation and reinforcement learning. We show how a probabilistic rule-based argumentation framework can capture Markov decision processes and reinforcement learning agentsen
dc.description.abstractand how the framework allows us to characterise agents and their argument-based motivations from both a logic-based perspective and a probabilistic perspective. We advocate and illustrate the use of our approach to capture models of agency and norms, and argue that, in addition to providing a novel method for investigating agent types, the unified framework offers a sound basis for taking a mentalistic approach to agent profiles.en
dc.description.sponsorshipMarie Curie Intra-European Fellowship European Union (EU) [PIEFGA-2012-331472]en
dc.language.isoen
dc.publisherSpringeren
dc.relation.ispartofAutonomous agents and multi-agent systemsen
dc.subjectProbabilistic argumentationen
dc.subjectMarkov decision processen
dc.subjectReinforcement learningen
dc.subjectNormsen
dc.titleA probabilistic argumentation framework for reinforcement learning agents : towards a mentalistic approach to agent profilesen
dc.typeArticle
dc.identifier.doi10.1007/s10458-019-09404-2
dc.identifier.volume33
dc.identifier.startpage216
dc.identifier.endpage274
eui.subscribe.skiptrue
dc.identifier.issue1-2


Files associated with this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record