Why using the game result instead of evaluation scores

Discussion of chess software programming and technical issues.

Moderators: hgm, Dann Corbit, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
User avatar
Posts: 708
Joined: Mon Dec 15, 2008 10:45 am

Re: Why using the game result instead of evaluation scores

Post by Desperado » Wed Jan 13, 2021 8:53 am

Desperado wrote:
Tue Jan 12, 2021 8:51 pm
Gerd Isenberg wrote:
Tue Jan 12, 2021 8:20 pm
I got that a little bit later. One needs to scale the engine specific score to a win percentage sigmoid for a 0-1 or -1,0,1 range.
Similar to TD(λ) one may even try to interpolate the final result into that score. I don't know whether this was tried before.
Well, something like rnbqkbnr/pppppppp/8/8/8/8/PPPPPPPP/RNBQKBNR w KQkq - ce 23
instead of rnbqkbnr/pppppppp/8/8/8/8/PPPPPPPP/RNBQKBNR w KQkq - "1/2-1/2"

then using

sigmoidInverse(23,400) as error reference.
Sorry my fault this time, i meant Sigmoid(23,400) not the inversed function. Of course i want to get the probability.

User avatar
Posts: 25520
Joined: Fri Mar 10, 2006 9:06 am
Location: Amsterdam
Full name: H G Muller

Re: Why using the game result instead of evaluation scores

Post by hgm » Wed Jan 13, 2021 9:39 am

The problem with search is that it usually doesn't compensate strategic misconceptions of the engine, unless it is very deep. It is mainly a method to detect tactics, and recognize that the root position is not quiet, so that the static evaluation of it is not really meaningful.

It would be useful to train a NN on evaluations corrected by shallow search when your goal is to have the NN predict tactics. But for NNs that will be used only in quiet positions of a search, that would not be a useful goal.

Just learning a NN to mimic a given static evaluation of an engine (or the average of a group of engines) with a hand-crafted eval doesn't seem a useful goal either. The hand-crafted eval probably can probably calculate that orders of magnitude faster. You want NNs because they can in principle do so much better than hand-crafted evals.

Post Reply