Multiobjective evolutionary algorithms have long been applied to engineering problems. Lately they have also been used to evolve behaviors for intelligent agents. In such applicat...
Evolutionary computation is used to construct undetectable computer attack scripts. Using a simulated operating system, we show that scripts can be evolved to cover their tracks a...
Many interesting problems, such as power grids, network switches, and tra c ow, that are candidates for solving with reinforcement learningRL, alsohave properties that make distri...
Jeff G. Schneider, Weng-Keen Wong, Andrew W. Moore...
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. ...
This paper describes the application of evolutionary search to the problem of Flash memory wear-out. The operating parameters of Flash memory are notoriously difficult to determin...