Classifier-based policy representationClassifier-based policy representation Πλήρης Δημοσίευση σε Συνέδριο Conference Full Paper 2015-11-132008enMotivated 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.http://creativecommons.org/licenses/by/4.0/91–982008 IEEE International Conference on Machine Learning and ApplicationsProceedings of the 2008 IEEE International Conference on Machine Learning and Applications (ICMLA), San Diego, CA, USA, December 2008 Rexakis Ioannis Ρεξακης Ιωαννης Lagoudakis Michael Λαγουδακης Μιχαηλ Institute of Electrical and Electronics Engineers Machine Learning