Author: Albert Silver
Date: 20:31:05 04/07/04
Go up one level in this thread
On April 06, 2004 at 20:16:25, Dann Corbit wrote: >http://tempo.runatomic.com/euroGP2004/siframes.html Fascinating. I wonder how much the author might benefit from studying the way neural net technology has been used to develop the latest crop of backgammon programs: Snowie 4 and GNU Backgammon. Interestingly enough, GNU Backgammon is actually the strongest one around. I even authored the tutorial on it at http://www.bkgm.com/gnu/AllAboutGNU.html The author of the neural nets is Joseph Heled, who keeps a detailed online journal (http://pages.quicksilver.net.nz/pepe/ngb/index.html - at bottom left be sure to change 'concise' for 'full') on the work he has done on them and his methodlogy and results. For example, in backgammon, more than one neural net was developed to cover different aspects of the game. The largest and most complex one is certainly the middlegame neural net, aka the contact net. Unfortunately, programs were absolutely abysmal when it came to races, where there wasn't any contact between the checkers of the players, and precise maximalization of the dice was necessary to achieve the best plays. Older programs were disastrous in this, so a special neural net was developed to deal with such situations. The programs also have look-ahead of course, and yes, it will consult the race net if it sees it could encounter a race situation 2 plies ahead. Perhaps developing some special nets for endgames, or even subsets of endgames, or whatnot, might also be possible. Also note that the previous technology developed by Gerald Tesauro (http://researchweb.watson.ibm.com/massive/tdl.html) presented limitations in its progress, as documented by Heled, and special training was done to further its development. Albert
This page took 0.03 seconds to execute
Last modified: Thu, 07 Jul 11 08:48:38 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.