Convergence of Synchronous Reinforcement Learning with Linear Function Approximation Artur Merke Lehrstuhl Informatik 1, University of Dortmund, 44227 Dortmund, Germany - Synchronous learning - Document - PDFSEARCH.IO

First Page	Meta Content
	Convergence of Synchronous Reinforcement Learning with Linear Function Approximation Artur Merke Lehrstuhl Informatik 1, University of Dortmund, 44227 Dortmund, Germany Add to Reading List Document Date: 2008-12-01 11:19:53 Open Document File Size: 129,83 KB Share Result on Facebook City Lancaster / Banff / / Company MIT Press / Baird L. C. / / Country Jordan / Canada / / / Facility University of Dortmund / Institute of Logic / University of Karlsruhe / / IndustryTerm synchronous residual gradient algorithm / residual gradient algorithm / hand algorithms / on-line behaviour / reinforcement learning algorithms / linear systems / time-variant discretetime systems / / Organization Institute of Logic / Complexity and Deduction Systems / University of Karlsruhe / University of Dortmund / MIT / / Person Van Roy / Ralf Schoknecht / Artur Merke Lehrstuhl Informatik / / Product Pentax K-x Digital Camera / / ProgrammingLanguage C / / PublishedMedium Machine Learning / / Technology synchronous RL algorithms / reinforcement learning algorithms / uniform RL algorithm / One algorithm / RL algorithms / RG algorithm / residual gradient algorithm / Machine Learning / RL algorithm / one hand algorithms / synchronous residual gradient algorithm / / SocialTag Root-finding algorithms Mathematical analysis Spectrum Numerical linear algebra Reinforcement learning Least squares Mathematical optimization Numerical analysis Mathematics Spectral theory

Convergence of Synchronous Reinforcement Learning with Linear Function Approximation Artur Merke Lehrstuhl Informatik 1, University of Dortmund, 44227 Dortmund, GermanyAdd to Reading List