Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...
In this paper, we propose a new modification of Cartesian Genetic Programming (CGP) that enables to optimize digital circuits more significantly than standard CGP. We argue that co...
In a preliminary part of this paper, we analyze the necessity of randomness in evolution strategies. We conclude to the necessity of ”continuous”-randomness, but with a much m...