A bayesian reinforcement learning framework using relevant vector machines

dc.contributor.author	Blekas, K.	en
dc.contributor.author	Tziortziotis, N.	en
dc.date.accessioned	2015-11-24T17:02:29Z
dc.date.available	2015-11-24T17:02:29Z
dc.identifier.uri	https://olympias.lib.uoi.gr/jspui/handle/123456789/11059
dc.rights	Default Licence	-
dc.title	A bayesian reinforcement learning framework using relevant vector machines	en
heal.abstract	In this work we present an advanced Bayesian formulation to the task of control learning that employs the Relevance Vector Machines (RVM) generative model for value function evaluation. The key aspect of the proposed method is the design of the discount return as a generalized linear model that constitutes a wellknown probabilistic approach. This allows to augment the model with advantageous sparse priors provided by the RVM s regression framework. We have also taken into account the significant issue of selecting the proper parameters of the kernel design matrix. Experiments have shown that our method produces improved performance in both simulated and real test environments.	en
heal.access	campus	-
heal.fullTextAvailability	TRUE	-
heal.journalName	AAAI	en
heal.journalType	peer reviewed	-
heal.language	en	-
heal.publicationDate	2011	-
heal.recordProvider	Πανεπιστήμιο Ιωαννίνων. Σχολή Θετικών Επιστημών. Τμήμα Μηχανικών Ηλεκτρονικών Υπολογιστών και Πληροφορικής	el
heal.type	journalArticle	-
heal.type.el	Άρθρο Περιοδικού	el
heal.type.en	Journal article	en

Αρχεία

Προβολή: 1 - 1 of 1