Rollout sampling approximate policy iterationRollout sampling approximate policy iteration Peer-Reviewed Journal Publication Δημοσίευση σε Περιοδικό με Κριτές 2015-10-272008enSeveral 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.Δημοσίευση σε επιστημονικό περιοδικό http://creativecommons.org/licenses/by/4.0/Machine Learning372 157-171 Dimitrakakis Christos Lagoudakis Michael Λαγουδακης Μιχαηλ Springer Verlag Reinforcement learning Approximate policy iteration Rollouts Bandit problems Classification Sample complexity