Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes Sridhar Mahadevan

First Page		Document Content
Date: 2013-04-06 12:45:57 Numerical analysis Linear algebra Abstract algebra Proto-value functions Spectral theory Dynamic programming Diffusion wavelets Nonlinear dimensionality reduction Reinforcement learning Mathematics Algebra Mathematical analysis		Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes Sridhar Mahadevan Add to Reading List Source URL: www-anw.cs.umass.edu Download Document from Source Website File Size: 3,71 MB Share Document on Facebook

	Polynomial Time Interactive Proofs for Linear Algebra with Exponential Matrix Dimensions and Scalars Given by Polynomial Time Circuits In memory of Wen-tsun Wu–Jean-Guillaume Dumas DocID: 1xUE0 - View Document
	1 Roadmap for the Development of a Linear Algebra Library for Exascale Computing SLATE: Software for Linear Algebra Targeting Exascale DocID: 1xUyc - View Document
	Recent Progress in Linear Algebra and Lattice Basis Reduction Gilles Villard CNRS, ENS de Lyon, INRIA, UCBL, Université de Lyon Laboratoire LIP DocID: 1xUmT - View Document
	3 Designing SLATE SLATE: Software for Linear Algebra Targeting Exascale Jakub Kurzak Panruo Wu DocID: 1xT5s - View Document
	9. Linear Algebra Po-Shen Loh CMU Putnam Seminar, Fall DocID: 1vrLR - View Document