[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [gnugo-devel] arend_1_22.2: tuning, regression test, --experimental-
From: |
Arend Bayer |
Subject: |
Re: [gnugo-devel] arend_1_22.2: tuning, regression test, --experimental-influence (fwd) |
Date: |
Wed, 23 Jan 2002 03:40:40 +0100 (CET) |
> > (It essentially consists of the two lines:
> > float diff = ( q->white_influence[i][j] - q->black_influence[i][j] )
> > /( q->white_influence[i][j] + q->black_influence[i][j] );
> > q->territory_value[i][j] = diff * diff * diff;
> > )
> >
> It's probably necessary to have a special case when both influence
> values are very small.
Yes, I realized that.
> > What I will have to do additionally is to do some retuning of the
> > influence patterns. At the moment, it makes hardly any difference whether
> > an influence source of strength 0.3 or 0.6 is added (if the opponent has
> > strength there, he will get a moyo in both cases). Also, at the moment,
> > e.g. the I patterns seem to have some inconsistencies. What I will have
> > to do there can probably go directly in the non-experimental version.
>
> There's certainly much to do there with tuning. I have only tuned it
> so far that it avoids the worst strangenesses. One thing to be careful
> with is early positions in high handicap games, where placing a stone
> in an area where previously only the opponent had stones can cause
> huge influence swings.
Hmm, actually, these big swings are maybe not wrong. It would create
such a big swing if one wouldn't get the trouble of creating another
weak group.
> Go ahead. The influence code has a lot of possibilities but it takes
> much experimentation to find out how best to make use of them.
Sure I will, just got distracted by two other smaller projects --
eliminating some of the FAILs caused by --owl-threats (not sure whether
I will send a patch, I am not yet very successful) and introducing
alpha-beta cut into the reading code.
Arend