Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Using GNU Chess to generate sample data for Behaviour Cloning

Author: Georg v. Zimmermann

Date: 05:55:49 11/10/03

Go up one level in this thread


Hi,

the suggestion to use Xboard in the other reply is a very good one of course.
That should give you the required data.

Your project sounds very interesting. I am afraid it might be a lot tougher than
you expect it to be, but I wish success.

Please keep us informed about the process and if you have further questions !

Georg


On November 10, 2003 at 03:22:38, Alex Holland wrote:

>I'm not actually seeking to create a chess program, as such - everything is
>going to be done in Prolog, using the Aleph machine learning package. I'm
>basically creating a system that, given a board state, will say "What would GNU
>Chess do?" and return a move. This move will have been decided inductively using
>a database of GNU Chess moves as statistical examples. What's important is that
>this move is similar or identical to the play of GNU Chess, rather than that
>this move is particularly good (although GNU Chess is pretty good, so hopefully
>it will be).
>
>This program may later be integrated into a chess program, but that's neither
>here nor there; this is all quite strictly academic.
>
>Alex



This page took 0.01 seconds to execute

Last modified: Thu, 15 Apr 21 08:11:13 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.