Vis enkel innførsel

dc.contributor.authorYazidi, Anis
dc.contributor.authorZhang, Xuan
dc.contributor.authorLei, Jiao
dc.contributor.authorOommen, John
dc.date.accessioned2019-03-14T14:28:19Z
dc.date.accessioned2019-06-27T08:59:23Z
dc.date.available2019-03-14T14:28:19Z
dc.date.available2019-06-27T08:59:23Z
dc.date.issued2018-05-22
dc.identifier.citationYazidi A, Zhang X, Lei J, Oommen J: The Hierarchical Continuous Pursuit Learning Automation for Large Numbers of Actions. In: Lazaros. Artificial Intelligence Applications and Innovations, 2018. Springer p. 451-461en
dc.identifier.isbn978-3-319-92006-1
dc.identifier.issn1868-4238
dc.identifier.urihttps://hdl.handle.net/10642/7238
dc.description.abstractAlthough the field of Learning Automata (LA) has made significant progress in the last four decades, the LA-based methods to tackle problems involving environments with a large number of actions are, in reality, relatively unresolved. The extension of the traditional LA (fixed structure, variable structure, discretized, and pursuit) to problems within this domain cannot be easily established when the number of actions is very large. This is because the dimensionality of the action probability vector is correspondingly large, and consequently, most components of the vector will, after a relatively short time, have values that are smaller than the machine accuracy permits, implying that they will never be chosen. This paper pioneers a solution that extends the continuous pursuit paradigm to such large-actioned problem domains. The beauty of the solution is that it is hierarchical, where all the actions offered by the environment reside as leaves of the hierarchy. Further, at every level, we merely require a two-action LA which automatically resolves the problem of dealing with arbitrarily small action probabilities. Additionally, since all the LA invoke the pursuit paradigm, the best action at every level trickles up towards the root. Thus, by invoking the property of the “max” operator, in which, the maximum of numerous maxima is the overall maximum, the hierarchy of LA converges to the optimal action. Apart from reporting the theoretical properties of the scheme, the paper contains extensive experimental results which demonstrate the power of the scheme and its computational advantages. As far as we know, there are no comparable results in the field of LA.en
dc.language.isoenen
dc.publisherSpringeren
dc.rightsThe final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-92007-8_38en
dc.subjectLearning Automataen
dc.subjectPursuit learning automataen
dc.subjectEstimator-based learning automataen
dc.subjectHierarchical learning automataen
dc.titleThe Hierarchical Continuous Pursuit Learning Automation for Large Numbers of Actionsen
dc.typeChapteren
dc.typePeer revieweden
dc.date.updated2019-03-14T14:28:19Z
dc.description.versionacceptedVersionen
dc.identifier.doihttps://dx.doi.org/10.1007/978-3-319-92007-8_38
dc.identifier.cristin1659914
dc.relation.projectIDUniversitetet i Agder: CIEM - Centre for Integrated Emergency Management
dc.source.isbn978-3-319-92006-1


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel