We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
This paper presents a hybrid technique that combines List Scheduling (LS) with Genetic Algorithms (GA) for constructing non-preemptive schedules for soft real-time parallel applic...
A rectilinear Steiner arborescence (RSA) is a tree, whose nodes include a prescribed set of points, termed the vertices, in the first quadrant of the Cartesian plane, and whose tr...
In some cases, evolutionary algorithms represent individuals as typical binary trees with n leaves and n-1 internal nodes. When designing a crossover operator for a particular rep...
We present the design, implementation, and evaluation of a Time Division Multiplex (TDM) MAC protocol for multihop wireless mesh networks using a programmable wireless platform. E...