The success ofreinforcement learninginpractical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experime...
In numerous applications of image processing, e.g. astronomical and medical imaging, data-noise is well-modeled by a Poisson distribution. This motivates the use of the negative-lo...
Domain-specific features are important in representing problem structure throughout machine learning and decision-theoretic planning. In planning, once state features are provide...
— We consider dual subgradient methods for solving (nonsmooth) convex constrained optimization problems. Our focus is on generating approximate primal solutions with performance ...
This paper introduces a novel algorithm to approximate the matrix with minimum nuclear norm among all matrices obeying a set of convex constraints. This problem may be understood a...