Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!helios!bcm!dimacs.rutgers.edu!seismo!uunet!wuarchive!emory!gatech!purdue!haven!umbc3!umbc5.umbc.edu!daren
From: daren@umbc5.umbc.edu (Daren Arnold (C))
Newsgroups: comp.ai.neural-nets
Subject: Game playing NN
Message-ID: <4947@umbc3.UMBC.EDU>
Date: 4 Feb 91 17:05:15 GMT
Sender: newspost@umbc3.UMBC.EDU
Reply-To: daren@umbc5.umbc.edu (Daren Arnold (C))
Distribution: na
Organization: University of Maryland, Baltimore County
Lines: 8

I have heard about a NN that learns to play a Pacman style game.  The
net is trained to avoid a certain color of dots, and attracted to another
color.

Could anybody refer me to a paper that describes this network?

Thanks for any help,
Daren