ECJ-INTEREST-L Archives

December 2005

ECJ-INTEREST-L@LISTSERV.GMU.EDU

Options: Use Monospaced Font
Show Text Part by Default
Condense Mail Headers

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

Print Reply
Sender:
ECJ Evolutionary Computation Toolkit <[log in to unmask]>
Date:
Fri, 30 Dec 2005 14:37:09 -0500
MIME-version:
1.0 (Apple Message framework v746.2)
Reply-To:
ECJ Evolutionary Computation Toolkit <[log in to unmask]>
Content-type:
text/plain; charset=US-ASCII; delsp=yes; format=flowed
Subject:
From:
Liviu Panait <[log in to unmask]>
In-Reply-To:
Content-transfer-encoding:
7bit
Comments:
To: ECJ Evolutionary Computation Toolkit <[log in to unmask]>
Parts/Attachments:
text/plain (21 lines)
I think the easiest approach is to implement your own statistics
(maybe extend SimpleStatistics).

> 1) How do I save the best-of-generation individual to a file each
> generation (or every N generations)?  My individuals are too large to
> print, and I'd like to do some other things with them after I evolve
> them.

In your new statistics, you just print that individual wherever you
want (screen, file, etc).

> 2) As mentioned, I'm coevolving Go players.  To see that I'm making
> progress, I'd like to test the best-of-generation individual against
> a random player and against a known good player every so many
> generations.  Is there any easy way to do this?

Again, you can do that in your custom statistics.  The
postEvaluationStatistics method looks perfect for both tasks.

Liviu.

ATOM RSS1 RSS2