Reinforcement Learning (RL) is analyzed here as a tool for control system optimization. State and action spaces are assumed to be continuous. Time is assumed to be discrete, yet th...
A simple learning rule is derived, the VAPS algorithm, which can be instantiated to generate a wide range of new reinforcementlearning algorithms. These algorithms solve a number ...
Architectures that exploit control independence (CI) promise to remove in-order fetch bottlenecks, like branch mispredicts, instruction-cache misses and fetch unit stalls, from th...
We describe “Belvedere,” a system to support students engaged in critical discussion of science and public policy issues. The design is intended to address cognitive and metac...
Massimo Paolucci, Daniel D. Suthers, Arlene Weiner
Establishing visual correspondences is an essential component of many computer vision problems, and is often done with robust, local feature-descriptors. Transmission and storage ...
Vijay Chandrasekhar, Gabriel Takacs, David M. Chen...