Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: History Heuristic

Author: Peter Fendrich

Date: 06:21:43 03/17/04

Go up one level in this thread


On March 17, 2004 at 07:35:03, Sune Fischer wrote:

>On March 17, 2004 at 06:53:44, Peter Fendrich wrote:
>
>>>I scale it down by a factor 8 when the entries hit a certain limit, ie.
>>>
>>>if (hist[index]>X)
>>>  for (i...)
>>>     hist[i]=hist_seed[i]+(hist[i]>>3);
>>
>>
>>This doesn't make sense to me. Maybe you meant to have the for-stmt before the
>>if-stmt? That's what I have tested a few times but without the hist_seed thing.

Oh, I see. index is pointing at the highest value. I've tried that too!
I have worked a lot with my history table...

>It's a form of normalizing the table, if you scale you must scale everything
>otherwise only the best entries gets cut down and not the bad ones.

I really thought that you tried some scrambling technique here!
It's maybe not be as bad as it sounds, the good moves will prove themself very
quickly again. The random part shouldn't be too dominating though.

/Peter

>>Is it a random seed and does that really help?
>
>It's not random, I just give a small static bonus for pawns to 7th and such so
>they don't zero out completely, seems those will always be interesting moves.
>
>>I have similar results as you but with much less differences than you between
>>the different frequencies. Without any seed though.
>
>-S.



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.