Re: [gnugo-devel] SlugGo v.s. Many Faces

[Douglas Ridgway]

On Tue, 24 Aug 2004, David G Doshay wrote:

> Thanks. Some of it is just the fun of winning; simple positive feedback 
> after
> a year of work. ;^)

I can understand that...

> We do plan to start a series of games against people, but they will
> have to be patient people. At the strongest levels we have found so
> far, it runs about 1/18th the speed of GNU Go.

You might try the turn-based servers, where 1 move/day is considered a 
fast game. The downside is that each game can take months. Also, I don't 
think there are automated interfaces.

> But before we do either there are some changes I would like to make in
> the code. I am not happy with the first 5 or so moves and need to
> implement a fix.

I was about to say, "First 5 moves? What can go wrong?" Then I looked at 
the games. 

I think you mentioned that the moves are selected based on a weighted 
combination of Gnugo's move valuations and your minimax search based score 
estimates. Would it help to adjust those weights during the course of the 
game? In the extreme case, you let Gnugo play the first five or ten moves 
by itself, then take over once the fighting starts. 

> > (*) I only see 24 games here, and I threw out the game with the unclear
> > result, so I worked with 23 games.
> 
> I was copying results by hand, so I must have slipped. Sorry. The missed
> entry is:
>       White wins by 25
> from the first set of 15, for which a link to the sgf files is given.

No problem. Including that result, the win rate becomes 79% (58%-93%),
score remains W+31 (W+12 - W+50), and p = 0.0033 on the binomial
distribution. Doesn't change much.

doug.