A bayesian reinforcement learning framework using relevant vector machines

Loading...
Thumbnail Image

Date

Authors

Blekas, K.
Tziortziotis, N.

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Type of the conference item

Journal type

peer reviewed

Educational material type

Conference Name

Journal name

AAAI

Book name

Book series

Book edition

Alternative title / Subtitle

Description

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.

Description

Keywords

Subject classification

Citation

Link

Language

en

Publishing department/division

Advisor name

Examining committee

General Description / Additional Comments

Institution and School/Department of submitter

Πανεπιστήμιο Ιωαννίνων. Σχολή Θετικών Επιστημών. Τμήμα Μηχανικών Ηλεκτρονικών Υπολογιστών και Πληροφορικής

Table of contents

Sponsor

Bibliographic citation

Name(s) of contributor(s)

Number of Pages

Course details

Endorsement

Review

Supplemented By

Referenced By