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

Search

Browse

My Space

Classifier-based policy representation

Rexakis Ioannis, Lagoudakis Michael

Simple record


URIhttp://purl.tuc.gr/dl/dias/2E55B7D4-6FCA-4907-8055-F24FEEF56CC9-
Identifierhttps://doi.org/10.1109/ICMLA.2008.31-
Languageen-
Extent8 pagesen
TitleClassifier-based policy representationen
CreatorRexakis Ioannisen
CreatorΡεξακης Ιωαννηςel
CreatorLagoudakis Michaelen
CreatorΛαγουδακης Μιχαηλel
PublisherInstitute of Electrical and Electronics Engineersen
Content SummaryMotivated by recent proposals that view a reinforcement learning problem as a collection of classification problems, we investigate various aspects of policy representation using classifiers. In particular, we derive optimal policies for two standard reinforcement learning domains (inverted pendulum and mountain car) in both deterministic and stochastic versions and we examine their internal structure. We then proceed in an evaluation of the representational ability of a variety of classifiers for these policies, using both a multi-class and a binary formulation of the classification problem. Finally, we evaluate the actual performance of the policies learned by the classifiers in the original control problem as a function of the amount of training examples provided. Our results offer significant insight in making the reinforcement-learning-via-classification technology successfully applicable to hard learning problems.en
Type of ItemΠλήρης Δημοσίευση σε Συνέδριοel
Type of ItemConference Full Paperen
Licensehttp://creativecommons.org/licenses/by/4.0/en
Date of Item2015-11-13-
Date of Publication2008-
SubjectMachine Learningen
Bibliographic CitationI. Rexakis and M. G. Lagoudakis, “Classifier-Based Policy Representation,” in 2008 IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 91–98. doi:10.1109/ICMLA.2008.31en

Services

Statistics