RE: [computer-go] Statistical significance (was: SlugGo vs Many Faces,newest data)

["Anders Kierulf" <anders@xxxxxxxxxxx>]

> Select positions random N steps into an opening book, allowing
> the database to reflect "real" playing. The opening book could
> be a standard one built from the games of high-level players or
> selected from games of players approximately the same strength
> as the go playing program.
>
> cheers
> stuart

This is exactly what SmartGo does when playing a series of games using the
Tools > Tourney command. It ships with SGF files containing suitable unique
opening positions:
- 50 opening positions for 9x9 games (4 moves into the game)
- 65 opening positions for 13x13 games (6 moves into the game)
- 100 opening positions for 19x19 games (8 moves into the game)

I also use the same technique for endgame testing, using early endgame
positions taken from professional games that end in half-point wins.

Anders Kierulf
www.smartgo.com


_______________________________________________
computer-go mailing list
computer-go@xxxxxxxxxxxxxxxxx
http://www.computer-go.org/mailman/listinfo/computer-go/