Author: Robert Hyatt
Date: 19:10:01 07/23/00
Go up one level in this thread
On July 23, 2000 at 10:03:51, Alessandro Damiani wrote: >On July 22, 2000 at 22:21:19, Robert Hyatt wrote: > >>On July 22, 2000 at 04:47:14, Graham Laight wrote: >> >>>Looks like Ed doesn't want to continue this thread any more, which is >>>understandable, because if he does, he could end up revealing more about how he >>>does evaluation than he really wants to. >>> >>>So - if anyone reading this knows how knowledge in Crafty is organised, could >>>they post an overview here, please, so that we can continue this thread? >>> >>>Thanks for your help with this. >>> >>>-g >> >> >>This is not easy to answer. But here is a rough explanation. >> >>First, there are several knowledge 'modules' that are called when >>appropriate. IE before both sides have castled and developed all pieces, >>there is an EvaluateDevelopment() modules that is called. Once this has >>done its job, it is disabled for the rest of the game. There are similar >>modules for mating the opponent, evaluating passed pawns, evaluating >>passed pawn races, and so forth. And they are only called when it is >>appropriate. >> >>The rest is more complex. There are many 'major' terms... king safety, >>endgame outlook (ie passed pawns, outside passed pawns, pawn majorities, >>and so forth). These terms are phased in based on remaining material. IE >>king safety is multiplied by using three factors; 1 is the pawn structure >>around the king, 2 is the pieces of the opponent and how dangerous they >>appear to be (how close and how many are close) and 3 remaining material. >>As material is removed, king safety scores are scaled down. >> >>By the same token, as material is removed, endgame predictors are scaled >>up (ie an outside passed pawn becomes more valuable). >> >>This is all what I call "third order evaluation" since three complex factors >>are used to compute a number... >> > >I think you took care of smoothness (SNAC)? > >Alessandro Yes. Everything is scaled from the original position, so there are no discontinuties in the evaluation at odd spots, except for a couple of minor ones dealing with the root-processing (very minor) that I still do. It is being phased out slowly, with a big chunk removed in 17.12 and more in 17.13.
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.