Hi Helene,

Le 01/06/2017 à 14:50, Hélène Arduin a écrit :
> Hi,
>
> Thank you Alberto for the explanation!
>
> Anyone on the parallelism parameter? I don't understand if the
> parallel generations are drawn simultaneously, computed and then
> regrouped before moving to the next ones, or if they are completely
> independent, or something else?

the genetic algorithm are implement in there steady state version (as
opposed to generational). It means that you'll have a pool of n
concurent evaluations (running on different nodes). A soon a an
evaluation is terminated the result is merged to the global population
and an new evaluation (or job) is created.

Does it answer your question?

Romain

>
> Hélène
>
>
> _______________________________________________
> OpenMOLE-users mailing list
> [email protected]
> http://fedex.iscpif.fr/mailman/listinfo/openmole-users


Attachment: signature.asc
Description: OpenPGP digital signature

_______________________________________________
OpenMOLE-users mailing list
[email protected]
http://fedex.iscpif.fr/mailman/listinfo/openmole-users

Reply via email to