Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Rollout sampling approximate policy iteration

Dimitrakakis Christos, Lagoudakis Michael

Simple record

URIhttp://purl.tuc.gr/dl/dias/157117EC-5401-47A1-B453-9D39AAFFC2E2-
Identifierhttps://doi.org/10.1007/s10994-008-5069-3-
Languageen-
Extent14en
TitleRollout sampling approximate policy iterationen
Creator Dimitrakakis Christosen
CreatorLagoudakis Michaelen
CreatorΛαγουδακης Μιχαηλel
PublisherSpringer Verlagen
DescriptionΔημοσίευση σε επιστημονικό περιοδικό el
Content SummarySeveral researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervised learning problem. This paper proposes variants of an improved policy iteration scheme which addresses the core sampling problem in evaluating a policy through simulation as a multi-armed bandit machine. The resulting algorithm offers comparable performance to the previous algorithm achieved, however, with significantly less computational effort. An order of magnitude improvement is demonstrated experimentally in two standard reinforcement learning domains: inverted pendulum and mountain-car.en
Type of ItemPeer-Reviewed Journal Publicationen
Type of ItemΔημοσίευση σε Περιοδικό με Κριτέςel
Licensehttp://creativecommons.org/licenses/by/4.0/en
Date of Item2015-10-27-
Date of Publication2008-
SubjectReinforcement learning en
SubjectApproximate policy iteration en
SubjectRollouts en
SubjectBandit problemsen
SubjectClassificationen
SubjectSample complexityen
Bibliographic CitationC. Dimitrakakis and M. G. Lagoudakis "Rollout sampling approximate policy iteration," Machine Learning, vol. 72, no. 3, pp. 157-171, Sept. 2008. doi: 10.1007/s10994-008-5069-3en

Services

Statistics

 

Copyright © DIAS 2013