We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
The distribution of data in large dynamic wireless sensor networks presents a difficult problem due to node mobility, link failures, and traffic congestion. In this paper, we pr...
David Dorsey, Bjorn Jay Carandang, Moshe Kam, Chri...
In this paper we present a swarm grammar system that makes use of bio-inspired mechanisms of reproduction, communication and construction in order to build three-dimensional struc...
An agent population can be evolved in a complex environment to perform various tasks and optimize its job performance using Learning Classifier System (LCS) technology. Due to the...