Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Parameter Tuning

Author: jonathan Baxter

Date: 15:19:59 10/02/98

Go up one level in this thread


On October 02, 1998 at 04:05:12, Ernst A. Heinz wrote:

>On October 01, 1998 at 20:28:55, jonathan Baxter wrote:
>>
>>Currently I am working on an improved version of KnightCap, with better
>>search and a much *simpler* evaluation function. Interesting preliminary
>>results
>>show that with parameter learning and *just* piece/square tables we can get
>>a rating of around 2500 on ICC.
>
>If I do not grossly misinterpret your PST values in connection with your
>above statement, then the final result seems to imply that in your games
>on ICC *material* is simply the dominating factor.

Material is definitely dominating. But for ordering materially equal positions,
the learnt piece/square tables do a pretty good job.


>
>Have you tried which ratings "KnightCap" achieves with good hand-tuned PSTs?
>

No, but they'd probably be similar. we have a very good understanding of the
"right" values for PSTs, so they are easy for us to tune.

Cheers,

Jonathan Baxter

>=Ernst=



This page took 0.14 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.