Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!unix.cis.pitt.edu!dsinc!netnews.upenn.edu!grad1.cis.upenn.edu!jrush
From: jrush@grad1.cis.upenn.edu (Thomas J. Rush)
Newsgroups: comp.ai.neural-nets
Subject: The pole balancing problem
Message-ID: <39423@netnews.upenn.edu>
Date: 20 Mar 91 00:38:03 GMT
Sender: news@netnews.upenn.edu
Reply-To: jrush@grad1.cis.upenn.edu (Thomas J. Rush)
Distribution: usa
Organization: University of Pennsylvania
Lines: 24
Nntp-Posting-Host: grad1.cis.upenn.edu

From: jrush@grad1.cis.upenn.edu (Thomas J. Rush)
Path: grad1.cis.upenn.edu!jrush
Newsgroups: comp.ai.neural-nets
Subject: The pole balancing problem
Expires: 
References: 
Sender: 
Reply-To: jrush@grad1.cis.upenn.edu (Thomas J. Rush)
Followup-To: 
Distribution: usa
Organization: University of Pennsylvania
Keywords: 


In the book "Neurocomputing - Foundations of Research" there is a paper 
by Barto, Sutton and Anderson called "Neuronlike adaptive elements that
can solve ...".  The paper describes a neural network that control a cart
which learns how to balance a pole based on applying a force in one
direction or another.

I would greatly appreciate any references to any papers that extend
or improve this idea.  

Thanks in advance, e-mail please.