Abstract. We investigate the problem of using function approximation in reinforcement learning where the agent’s policy is represented as a classifier mapping states to actions....
Aspect oriented programming (AOP), when used well, has many advantages. Aspects are however, programming-time constructs, i.e., they relate to source code. Previously, we develope...
John A. Stankovic, Prashant Nagaraddi, Zhendong Yu...
The BlueGene/L supercomputer will consist of 65,536 dual-processor compute nodes interconnected by two high-speed networks: a three-dimensional torus network and a tree topology ne...
The cost functions used to evaluate logic synthesis transformations for FPGAs are far removed from the final speed and routability determined after placement, routing and timing a...
We have already proposed using evolutionary computation to adjust the voice quality conversion parameters, and we have reported that this approach produces results that are not onl...