A method for the determination of the progress rate and the probability of success for the Evolution Strategy (ES) is presented. The new method is based on the asymptotical behavior of the χ-distribution and yields exact results in the case of infinite-dimensional parameter spaces. The technique is demonstrated for the (l,+ λ) ES using a spherical model including noisy quality functions. The results are used to discuss the convergence behavior of the ES.

Evolution Strategy (ES), (1,+ λ), spherical model, noisy fitness, theory, rate of progress, optimization, mutation-selection principle
This content is only available as a PDF.
© 1993 by the Massachusetts Institute of Technology
1993
You do not currently have access to this content.