Newsgroups: comp.ai.games
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!zombie.ncsc.mil!news.duke.edu!news-feed-1.peachnet.edu!gatech!howland.reston.ans.net!EU.net!CERN.ch!cs2-3!ransen
From: ransen@cerncs2.cern.ch (owen ransen)
Subject: neural nets for backgammon
X-Nntp-Posting-Host: cerncs2-3.cern.ch
Message-ID: <D5Foqn.E7C@news.cern.ch>
Keywords: backgammon  ai  neural nets 
Sender: news@news.cern.ch (USENET News System)
Reply-To: ransen@cerncs2.cern.ch (owen ransen)
Organization: CERN European Laboratory for Particle Physics
X-Newsreader: mxrn 6.18-16
Date: Tue, 14 Mar 1995 14:11:11 GMT
Lines: 12


I read in Dr.Dobbs about a year ago about a neural network
program which learned on it's own how to play backgammon.
I have tried myself to adapt a "statistical" backgammon
program to a C++ neurla network system but with abysmal results:
The stats version of the program easily beat the NN version of
the program.
Does anywone know who wrote the NN version metioned in Dr.Dobbs?
And are the sources freely available?
Thanx,
Owen

