Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!MathWorks.Com!yeshua.marcam.com!zip.eecs.umich.edu!newsxfer.itd.umich.edu!caen!msuinfo!harbinger.cc.monash.edu.au!news.cs.su.oz.au!metro!sedal.su.OZ.AU!schultz
From: schultz@sedal.su.OZ.AU ()
Subject: Re: Reinforcement learning, ref's wanted.
Message-ID: <Cxqnnw.EGB@ucc.su.OZ.AU>
Sender: schultz@sedal ()
Nntp-Posting-Host: sedal.sedal.su.oz.au
Organization: Information Services, Sydney University, Sydney, NSW, Australia
References:  <1994Oct14.150325.4752@bay.cc.kcl.ac.uk>
Date: Sat, 15 Oct 1994 23:52:43 GMT
Lines: 20

(My email reply bounced so I will post.)

Try:

"A neuronal model of classical conditioning", A. H. Klopf, Psychobiology 16(2) pp. 85-125.

"A hierarchical Network of Control Systems that Learn: Modeling Nervous System Function During Classical and Instrumental Conditioning", Klopf, Morgan, Weaver, Adaptive Behavior Vol. 1, No. 3, 263-319.

"Drive-Reinforcement learning: a self-supervised model for adaptive control", Morgan, Patterson, Klopf, Network 1(1990) 439-448

-----

    Simon Schultz,
    Systems Engineering & Design Automation Laboratory (SEDAL),
    Department of Electrical Engineering,
    University of Sydney, 2006.
    Australia.

    Phone: (02) 692 3297.	( +61-2 692 3297 )
    Fax:   (02) 660 1228.	( +61-2 660 1228 )
