Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
—Current visual analytics systems provide users with the means to explore trends in their data. Linked views and interactive displays provide insight into correlations among peop...
Ross Maciejewski, Ryan Hafen, Stephen Rudolph, Ste...
Numerical particle simulations and astronomical observations create huge data sets containing uncorrelated 3D points of varying size. These data sets cannot be visualized interact...
Abstract. The purpose of this article is to propose a scalable, topologically and traffic-wise self-adapting approach to a publish/subscribe paradigm for supporting event-based app...
We consider the problem of efficiently learning optimal control policies and value functions over large state spaces in an online setting in which estimates must be available afte...