When it comes to a search, one need to ask that is my evaluation function perfect? If not (in almost all cases), why should one use a search algorithm that assumes the evaluation function is perfect? UCT can work with an imperfect evaluation function. A perfect answer can be obtained if the evaluation function is perfect. In this case there is no significant difference between UCT and alpha-beta. However, this does not take into account of the possibility of the existence of an underlying structure in the evaluation values. This underlying structure is not exployed in alpha-beta. It is to some extent in a width first algorithm. Right now the significance of MC scoring is still a somewhat mystry. Also no one has mentioned what the search depths are for the UCT groprams. -----Original Message----- From: [EMAIL PROTECTED] To: computer-go@computer-go.org Sent: Fri, 6 Apr 2007 6:54 AM Subject: Re: [computer-go] The dominance of search (Suzie v. GnuGo)
Chrilly wrote: > I think on 9x9 the superiority of search based programms is now > clearly > demonstrated. Its only the question if UCT or Alpha-Beta is > superior. Hi Chrilly, Thanks for your report. The question of UCT versus Alpha-Beta is not open any more in my opinion. The current state of the art of Monte Carlo tree search is about 500 Elo points stronger than the version of Crazy Stone you tested against. Do you believe you can easily catch up with those 500 Elo points ? Also, I am convinced that UCT has tremendous potential for further improvement. I have improved Crazy Stone by about 50 Elo points per day in the past 10 days (on 9x9. The improvement on 13x13 and 19x19 is much more). I am very confident that I can easily improve it further very much. Rémi _______________________________________________ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ________________________________________________________________________ AOL now offers free email to everyone. Find out more about what's free from AOL at AOL.com.
_______________________________________________ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
