Christoph Birk wrote: >> Unfortunately, I used level 10 in the gnugo only games but in the big >> study we use level 8. It's my understanding there is little difference >> between these 2 but we can probably assume Mogo might be a little better >> than indicated relative to the big scalability study. > > Don't you think it would be more prudent to repeat the 'gnugo-only' > study using the same gnugo-level as in the big study before you > draw any conclusions? Perhaps, but it's a major pain running those games and it ties up my machine. I presented the data and explained the parameters so you can draw your own conclusions. Since I failed to use the correct Gnugo level you can take my conclusions with a grain of salt.
I may have another machine I can run this on, if so I will repeat it using 1000 games instead of 500 and using gnugo level 10 instead. - Don > > Christoph > > _______________________________________________ > computer-go mailing list > [email protected] > http://www.computer-go.org/mailman/listinfo/computer-go/ > _______________________________________________ computer-go mailing list [email protected] http://www.computer-go.org/mailman/listinfo/computer-go/
