File Exchange

image thumbnail

Evolution Strategies (ES)

version 1.1 (13.4 KB) by Gilberto A. Ortiz
Algorithm that implements 'Evolution Strategies' (ES) ('mu-lambda' and 'mu+lambda' variants).


Updated 20 Nov 2014

View License

This function uses ES to optimize a function f(x_1,...,x_n). There are a set of 55 test functions to check the effectiveness of the algorithm when optimizing functions.
Feel free to leave comments, corrections or suggestions. Read the comments in the code for more information and bibliography used in the development of this code.

Comments and Ratings (8)

well done, this implementaion is about self adaptation correlated mutation evoluton strategy.
it's was more interesting and complete if it's deal also with other kind of mutation such the uncorrelated mutations ( one step size and individual step size)
Thank you Author.



hi, could you share on how to implement this m file in simulink model for online optimization? i'm having difficulties on this.



sorry, in this code which variable represents optimal decision vector?

Thanks for your feedback ZHANG...


The implementation is very straightforward and good based on my opinion. However, the program becomes slow when tested by n_x=30, mu=lambda=100 after a few hundred generations. This may be the problem of Evolutionary Strategy itself not the implementation.



Update file as a Toolbox

MATLAB Release Compatibility
Created with R2010b
Compatible with any release
Platform Compatibility
Windows macOS Linux

Discover Live Editor

Create scripts with code, output, and formatted text in a single executable document.

Learn About Live Editor