Sridhar Mahadaven

Learning Representation and Control in Markov Decision Processes: New Frontiers - Foundations and Trends® in Machine Learning Sridhar Mahadaven

Describes methods for automatically compressing Markov decision processes (MDPs) by learning a low-dimensional linear approximation defined by an orthogonal set of basis functions. A unique feature of the text is the use of Laplacian operators, whose matrix representations have non-positive off-diagonal elements and zero row sums.