ECJ-INTEREST-L Archives

August 2006

ECJ-INTEREST-L@LISTSERV.GMU.EDU

Options: Use Proportional Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Robert Baruch <[log in to unmask]>
Reply To:
ECJ Evolutionary Computation Toolkit <[log in to unmask]>
Date:
Mon, 21 Aug 2006 15:09:06 -0400
Content-Type:
multipart/mixed
Parts/Attachments:
text/plain (811 bytes) , mille.params (10 kB)
Hi all,

I'm having some problems running GP with coevolution with more than one subpopulation. When I 
run my problem with only 1 subpop, the run goes fine. I am able to run every individual in the 
subpop against N random individuals in the same subpop.

Problem #1: What I would like to do is run every individual in every subpop against N random 
individuals from different subpops. Any idea on which parameters control this? Or do I have to write 
custom code, and if so, what do I need to modify?

Problem #2: When I run more than one subpop, it seems that the individuals generated for the 
second subpop are all only one terminal of the return type, as if the initializer is not generating 
individuals properly. Can someone shed light on this? I'm attaching my params file for your perusal.

Thanks for any help!

--Rob



ATOM RSS1 RSS2