[Scilab-users] CMA-ES boundary handling in scilab

Claus Futtrup cfuttrup at gmail.com
Thu Feb 27 20:07:29 CET 2014


Hi Natasha

I have several years of experience with CMA-ES. I am also the author of 
the Scilab ATOMS module you can find here:

https://atoms.scilab.org/toolboxes/CMA-ES

I am well aware the code is not working well with Scilab (i.e. if you 
install the ATOMS module it does something bad to your Scilab and the 
Scilab GUI doesn't work).

I don't know what to do about it (need help from Scilab experts). You 
could say, Scilab needs to document their ATOMS properly, so that 
independent people (like me) can make fully working ATOMS modules.

Regarding search space, I have successfully implemented much of this. 
You can write me in private ( cfuttrup -at- gmail.com ), not to 
unnecessarily disturb this Scilab forum.

Best regards,
Claus

On 2/27/2014 19:57, natasha wrote:
> Hello everyone,
>
> I am currently working on translating an optimization problem (solved with
> CMA-ES) from Matlab to Scilab.
>
> If I have understood properly cma_optim does not contain any Matlab
> equivalent option of optsLB, opts.UB .
>
> In the source page there is a comment on boundary handling
> https://www.lri.fr/~hansen/cmaes_inmatlab.html
> <https://www.lri.fr/~hansen/cmaes_inmatlab.html>  .
>
> Has anyone ever tried establishing a search space for the CMA-ES in Scilab?
>
> Thank you very much for your attention, Anastasia
>
>
>
>
>
> --
> View this message in context: http://mailinglists.scilab.org/CMA-ES-boundary-handling-in-scilab-tp4029013.html
> Sent from the Scilab users - Mailing Lists Archives mailing list archive at Nabble.com.
> _______________________________________________
> users mailing list
> users at lists.scilab.org
> http://lists.scilab.org/mailman/listinfo/users
>


---
This email is free from viruses and malware because avast! Antivirus protection is active.
http://www.avast.com




More information about the users mailing list