Petr Baudis wrote: > On Sun, Jun 27, 2010 at 08:49:57PM +0900, Darren Cook wrote: >>>> I guess moving to whole board patterns doesn't actually add much CPU, >>>> because they are only 3x3: a list of matching patterns can be >>>> maintained, and after each move only a few points need to be considered >>>> for new pattern matches.
>>> Yes, but then you need to choose from a probability distribution over >>> all the moves, which actually does slow things down *quite* a lot. >>> But apparently the slowdown is worth it. >> That is the Crazy Stone way? I imagined Fuego's way: just have a list of >> moves and choose one of them randomly. > > Fuego does not check patterns over the whole board, ... I didn't mean like Fuego in that way. I mean when Fuego has a list of equally valid moves to choose from, it chooses one randomly (they are kept in an array). No weights, no probability distributions. There are two ideas here: * Consider whole board, not just around last move; * Use pattern weights Crazy stone does both together, and by the sounds of it Many Faces, Pachi and Zen do too. I was saying just doing the first idea might be worth the small effort keeping the list of moves: when no local pattern matches, and a random move would otherwise be chosen, consider a pattern move leftover from another part of the board. Darren -- Darren Cook, Software Researcher/Developer http://dcook.org/gobet/ (Shodan Go Bet - who will win?) http://dcook.org/work/ (About me and my work) http://dcook.org/blogs.html (My blogs and articles) _______________________________________________ Computer-go mailing list [email protected] http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
