Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: The importance of learning

Author: Tord Romstad

Date: 10:11:35 01/14/04

Go up one level in this thread


On January 14, 2004 at 12:51:32, Peter Fendrich wrote:

>Of course it can be random fluctuations but i have run several matches with and
>without learning. I can tell you that aggressive learning vs an opponent with a
>tiny book will eventually crush that opponent. The same goes if the opponent
>have a bad book. It makes a big difference quickly. Aggressive learning vs an
>opponent with a good big wide and "bushy" book is not at all that effective.

Gothmog's book can best be described as "bad, wide and bushy".  It plays
almost everything, including openings it doesn't understands at all (I really
hate to see it play the Benko gambit).

>It can even be the other way around you will "overlearn" unimportant things. Less
>aggressive learning is better in that case and it will then take a longer time
>before you see any results from the learning.
>I have no idea what kind of learning Phalanx is using.

Neither have I.  I have just started another 100-game match on the PIV 2.4 GHz,
this time with learning enabled for Phalanx.  Gothmog won the first two games.

Thanks to you and everybody else for the answers!

Tord



This page took 0 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.