MDP / Gram matrix KG / Cambridge University Press / MIT Press / Laplacian / /
Country
Germany / United States / / /
Facility
University of Massachusetts / Yale University / /
IndustryTerm
open chain / non-symmetric random walk operator / random walk operator / inner product / node chain / symmetric operator / symmetric self-adjoint operator / positive definite inner products / random walk diffusion operator / closed chain / self-adjoint operator / open and closed chain / proto-reinforcement learning algorithms / /
Organization
Cambridge University / National Science Foundation / American Mathematical Society / Department of Computer Science / MIT / Department of Mathematics / University of Massachusetts / Amherst / Yale University / Pattern Analysis and Machine Intelligence / Department of Mathematics at Yale University / /
Proto-Value Functions: Developmental Reinforcement Learning Sridhar Mahadevan