Computer Chess Club Archives




Subject: Re: chess and neural networks

Author: Sune Fischer

Date: 14:52:59 07/06/03

Go up one level in this thread

On July 06, 2003 at 17:38:01, Vincent Diepeveen wrote:

>If there was money to earn by programming a backgammon engine, i am sure some
>guys who are good in forward pruning algorithms like Johan de Koning would win
>every event there. It's like making a tictactoe program and then claiming that
>an ANN is going to work.
>As we have a saying here: "In the land of the blind, one eyed is King".
>That's why i focus upon chess.
>In contradiction to you, i know how to do it with ANNs (just like many others
>do), i just don't have 10^1000 system time to actually let the learning
>algorithm finish ;)
>Any approximation in the meantime will be playing very lousy chess...
>Hell, with 10^1000 runs, even TD learning might be correctly finding the right
>parameter optimization :)
>TD learning is randomly flipping a few parameters each time. It's pretty close
>to GA's in that respect.

There might be tricks to speed that up, certainly can't rule it out before it
has been seriously attempted.

For example one could try and do some kind of "anti-aliasing" on the board, ie.
smear the whole thing, to make the patterns more general. This would require
only a fraction of the full network and make it faster to train.

I'm sure the ideas will come if people try it, what you see as problem others
may see as challenge :)


This page took 0.01 seconds to execute

Last modified: Thu, 07 Jul 11 08:48:38 -0700

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