step function of SState

Piet Kerckhove Piet.Kerckhove at rug.ac.be
Thu Jul 11 11:37:48 EDT 2002


This is indeed what happens, this makes the steadystate algortihm fast but not 
very robust when facing local optima (due to a lack of diversity). It might be 
better using IncrementalGA or SimpleGA.

Citeren Sanne Houweling <sanne at blade030.cs.vu.nl>:

> Dear all,
> 
> I am confused about the step() function of the SStateGA, in
> particular the selection.
> 
> The comment says: "If a genome in the tmp population is worse
> than one in the main population, the genome in the main
> population will be replaced regardless of its better score."
> 
> But what happens is adding the members of tmp_pop
> (containing offspring) to main_pop (containing preceeding
> pop), evaluating this union and then removing the worst
> tmp_pop_size individuals.
> 
> Regards, Sanne.
> 
> 
> ** Sanne Houweling  -  (+31)207705488   -   sanne at cs.vu.nl **
> ** Faculty of Exact Sciences - Vrije Universiteit Amsterdam**
> 
> 
> _______________________________________________
> galib mailing list
> galib at mit.edu
> http://lancet.mit.edu/mailman/listinfo/galib
> 


-- 
piet.kerckhove at rug.ac.be



More information about the galib mailing list