Please use this identifier to cite or link to this item: https://olympias.lib.uoi.gr/jspui/handle/123456789/11134
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLikas, A.en
dc.contributor.authorLagaris, I. E.en
dc.date.accessioned2015-11-24T17:03:08Z-
dc.date.available2015-11-24T17:03:08Z-
dc.identifier.issn1370-4621-
dc.identifier.urihttps://olympias.lib.uoi.gr/jspui/handle/123456789/11134-
dc.rightsDefault Licence-
dc.subjectreinforcement learningen
dc.subjectneurocontrolen
dc.subjectoptimizationen
dc.subjectpolytope algorithmen
dc.subjectpole balancingen
dc.subjectgenetic reinforcementen
dc.titleTraining reinforcement neurocontrollers using the polytope algorithmen
heal.typejournalArticle-
heal.type.enJournal articleen
heal.type.elΆρθρο Περιοδικούel
heal.languageen-
heal.accesscampus-
heal.recordProviderΠανεπιστήμιο Ιωαννίνων. Σχολή Θετικών Επιστημών. Τμήμα Μηχανικών Ηλεκτρονικών Υπολογιστών και Πληροφορικήςel
heal.publicationDate1999-
heal.abstractA new training algorithm is presented for delayed reinforcement learning problems that does not assume the existence of a critic model and employs the polytope optimization algorithm to adjust the weights of the action network so that a simple direct measure of the training performance is maximized. Experimental results from the application of the method to the pole balancing problem indicate improved training performance compared with critic-based and genetic reinforcement approaches.en
heal.journalNameNeural Processing Lettersen
heal.journalTypepeer reviewed-
heal.fullTextAvailabilityTRUE-
Appears in Collections:Άρθρα σε επιστημονικά περιοδικά ( Ανοικτά)



This item is licensed under a Creative Commons License Creative Commons