ChessUSA.com TalkChess.com
Hosted by Your Move Chess & Games
 
 FAQFAQ   SearchSearch   MemberlistMemberlist   UsergroupsUsergroups   RegisterRegister 
 ProfileProfile   Log in to check your private messagesLog in to check your private messages   Log inLog in 

Logarithmic Patterns In Evaluations
Post new topic    TalkChess.com Forum Index -> Computer Chess Club: Programming and Technical Discussions Flat
View previous topic :: View next topic  
Author Message
Dennis Sceviour



Joined: 20 Jul 2015
Posts: 319

PostPost subject: Re: Logarithmic Patterns In Evaluations    Posted: Sat Dec 09, 2017 11:15 pm Reply to topic Reply with quote

jdart wrote:
No, I am not saying hand tune mobility. I am saying, Knight with one square to move to gets one weight, and Knight with two squares to move to gets another weight. Both weights can be auto-tuned. They are independent.

I do not agree they are independent. They follow an average logarithmic pattern of increase.
Quote:
The reason you normalize is that the purpose of regularization is to penalize extreme values. So you want large values of the parameters (+ or -) to give larger penalties.

This can be approached from a different point of view. The following type of position is won for white in almost all queen positions:
[d]8/8/8/6k1/3Q2p1/8/5K2/8 w - - 0 1
   ::    ::    ::    ::
::    ::    ::    ::    
   ::    ::    ::    ::
::    ::    ::    BK    
   ::    WQ    :: BP ::
::    ::    ::    ::    
   ::    ::    WK    ::
::    ::    ::    ::    

Queen mobility numbers are irrelevant and a tuning number would give an infinite value. Thus, instead a test:
if whiteMaterial < 300 then ...
will bypass any mobility test on the static evaluation. Some static evaluators also call this a lazy evaluation cutoff.
Back to top
View user's profile Send private message Visit poster's website
Display posts from previous:   
Subject Author Date/Time
Logarithmic Patterns In Evaluations Dennis Sceviour Sat Dec 09, 2017 6:05 pm
      Re: Logarithmic Patterns In Evaluations Jon Dart Sat Dec 09, 2017 6:59 pm
            Re: Logarithmic Patterns In Evaluations Dennis Sceviour Sat Dec 09, 2017 7:21 pm
                  Re: Logarithmic Patterns In Evaluations Jon Dart Sat Dec 09, 2017 7:46 pm
                        Re: Logarithmic Patterns In Evaluations Dennis Sceviour Sat Dec 09, 2017 8:54 pm
                              Re: Logarithmic Patterns In Evaluations Jon Dart Sat Dec 09, 2017 10:51 pm
                                    Re: Logarithmic Patterns In Evaluations Dennis Sceviour Sat Dec 09, 2017 11:15 pm
                                          Re: Logarithmic Patterns In Evaluations Dennis Sceviour Sun Dec 10, 2017 2:29 pm
                                                Re: Logarithmic Patterns In Evaluations Jon Dart Sun Dec 10, 2017 8:34 pm
Post new topic    TalkChess.com Forum Index -> Computer Chess Club: Programming and Technical Discussions

 
Jump to:  
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum




Powered by phpBB © 2001, 2005 phpBB Group
Enhanced with Moby Threads