In this paper, it is shown how to extract a hypothesis with small risk from the ensemble of hypotheses generated by an arbitrary on-line learning algorithm run on an independent an...
We show that states of a dynamical system can be usefully represented by multi-step, action-conditional predictions of future observations. State representations that are grounded...
Michael L. Littman, Richard S. Sutton, Satinder P....
We propose a flexible approach for the visualization of large, high-dimensional datasets. The raw, highdimensional data is mapped into an abstract 3D distance space using the Fast...
HDPS is a practical system for designing modeling paradigms, creating hierarchal model definitions, and evaluating multi-paradigm models - particularly in business and finance. HD...
This paper presents an efficient and homogeneous paradigm for automatic acquisition and recognition of nonparametric shapes. Acquisition time varies from linear to cubic in the nu...