[computer-go] scalability study

[Łukasz Lew]

Try simple MC with all as first :)
I guess it beat any UCT totally.
( one playout here will be as 200-300 in UCT)

On 1/27/07, Don Dailey <drd at mit.edu> wrote:
> Below is the current results (in progress) of my
> UCT 19x19 GO scalability study.
>
> This is going to take a lot of time, but the
> results should be useful and I want to make
> them a matter of public record.   Each person
> will interpret the data however he/she chooses.
>
> The data below contains the following levels:
>
>   0001  - 1024 play-outs
>   0002  - 2048 play-outs
>   0004  - 4096 play-outs
>   0008  - 8192 play-outs
>
> With help from other I will extend this as
> much as possible to much higher levels.  Someone
> is helping me run games even now as I write
> this at higher levels - but the rate of play is
> quite slow, so it will be some time until we get
> significant results.
>
> Also please note this is not a round robin,  only
> matches between neighbor levels will be played.
> 2 vs 1,  4 vs 2,  8 vs 4,  16 vs 8  .... etc.
>
>    komi 7.5
>    200 games per match - 100 with each color
>
>
> - Don
>
>
>
>  games    win%   Match
> ------  ------   -------------
>     24   95.8%   0008     0004
>    151   94.7%   0004     0002
>    152   90.1%   0002     0001
>
>
>  Rating    Tot Gms    Player
> -------    -------    ------
>  1045.3         24    0008
>   678.7        175    0004
>   321.1        303    0002
>     0.0        152    0001
>
> Black wins:      159      48.6 %
> White wins:      168      51.4 %
>
>
>
> _______________________________________________
> computer-go mailing list
> computer-go at computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>