Rollout Sampling Approximate Policy Iteration

Simple item page
dc.creatorDimitrakakis, Christos
dc.creatorLagoudakis, Michail G.
dc.date2008-05-14
dc.date2008-07-06
dc.date.accessioned2026-07-07T09:48:22Z
dc.date.available2026-07-07T09:48:22Z
dc.descriptionSeveral 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.
dc.description18 pages, 2 figures, to appear in Machine Learning 72(3). Presented at EWRL08, to be presented at ECML 2008
dc.identifierhttps://arxiv.org/abs/0805.2027
dc.identifierhttp://arxiv.org/abs/0805.2027
dc.identifierdoi:10.1007/s10994-008-5069-3
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/164186
dc.subjectMachine Learning
dc.subjectArtificial Intelligence
dc.subjectComputational Complexity
dc.titleRollout Sampling Approximate Policy Iteration
dc.typetext

Files

Collections

arXiv