[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [computer-go] Competition of the GO-algorithms
Gunnar wrote:
> How finished are the games?
> Can there be an unfinished ko left on the board?
The Database hasn’t contained the games with an unfinished ko.
> Can there also be forced reinforcement moves (teire) omitted?
All reinforcement moves are placed on the board.
> I can answer the question about teire.
> There may be reinforcement moves omitted but those are
> not taken into account in the recorded score.
> E.g. in 026.sgf the position is and apparently
> white counts a point at J7.
I have checked example games and corrected 026.sgf and 043.sgf
> I think e.g. that you can get a decent score without a proper life
> and death analysis, using various heuristics which
> are only valid when the game is known to be finished.
I made attempt to use this heuristics, but lost out on that way,
only 25% of the problems have solved without life and death algorithm.
> Which version of GNU Go has been tested? Both GNU Go 3.6 and GNU Go
> 3.7.1 correctly score the example game 2527 on the web page.
Yes, it’s early. GNU Go 3.5.10
> Is the competition database available or is it planned to be kept
> secret?
The Database will be kept secret,
but some of the games were not solved by any algorithm
will be published to verify the correct result into the Database.
Alex Mel
_______________________________________________
computer-go mailing list
computer-go@xxxxxxxxxxxxxxxxx
http://www.computer-go.org/mailman/listinfo/computer-go/