On Sat, Feb 19, 2011 at 2:14 PM, Steve Safarik <[email protected]>wrote:
> Suppose I develop what I think is an improved feature, for example a > better influence function or some other. I'd like to hear people's thoughts > on how to best & most quickly determine if it is in fact an improvement. Do > I just take my new function and replace the equivalent function in something > like Fuego, then have the two engines start playing games? My impression is > that would be a rather slow way to get enough games to be of significance. > Is there a better way to compare two engines? If that is indeed the method > people generally use, how much time do you allow per move or game, and can > you tell me your general experiences with doing this? Thanks. > It's my view that there is no substitute for playing games. CGOS is one possibility, but you will get more games in if you set up your own testing infrastructure. In computer chess, I test changes by running (in some cases) several games per second. Even my longer tests are several games per minute (but using a 6 core i7.) In 19x19 go you will need more time per game of course. Unless your changes have a large effect on the strength, you must play thousands of games. Sorry, no shortcuts here. Don > > Steve. > > > > _______________________________________________ > Computer-go mailing list > [email protected] > http://dvandva.org/cgi-bin/mailman/listinfo/computer-go >
_______________________________________________ Computer-go mailing list [email protected] http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
