Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Aspiration Window sizes

Author: Robert Hyatt

Date: 19:47:16 03/14/05

Go up one level in this thread


On March 14, 2005 at 13:40:51, Harald Lüßen wrote:

>On March 14, 2005 at 10:05:24, Robert Hyatt wrote:
>
>>... Take your program, and try different values, over a
>>large test set of positions.  Find the range that produces
>>the greatest average search depth for the test set.
>>It will vary for each program, since the
>>evaluation functions can produce wildly variable scores...
>
>Does it make sense to change the window depending on
>the plies of the iterative deepening, the root evaluation
>or any other variable?
>
>Does someone make an extrapolation of the N last scores and
>build the window around it?
>
>Harald


I offset the window to handle odd-even iteration score swings, but that is all I
have played with other than the window width.  And I haven't even checked to see
that the current window size is optimal in at least 3 years if not longer...



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.