On the Quality Gain of (1, lambda)-ES under Fitness Noise
Beyer, H.-G. and Meyer-Nieberg, S. (2004), X. Yao et al.: Parallel Problem Solving from Nature 8, 1-10, Springer, Berlin
Abstract
In optimization tasks that deal with real-world applications noise is very common leading to degradation of the performance of Evolution Strategies. We will consider the quality gain of an (1, lambda)-ES under noisy fitness evaluations for arbitrary fitness functions. The equation developed will be applied to several test functions to check its predictive quality. www.springer.de
