DPRG
DPRG List  



DPRG: BOUNCE dprglist@dprg.org: Non-member submission from [Kipton Moravec <kmoravec@usa.net>]

Subject: DPRG: BOUNCE dprglist@dprg.org: Non-member submission from [Kipton Moravec <kmoravec@usa.net>]
From: Jim Brown jimbrown at airmail.net
Date: Sat Jan 10 10:25:08 CST 1998

>Return-Path: <owner-dprglist at dprg.org>
>Date: Fri, 9 Jan 1998 18:22:05 -0600
>From: owner-dprglist at dprg.org
>X-Authentication-Warning: horta.ncc.com: mail set sender to
owner-dprglist at dprg.org using -f
>To: owner-dprglist at dprg.org
>Subject: BOUNCE dprglist at dprg.org:    Non-member submission from [Kipton
Moravec <kmoravec at usa.net>]   
>
>>From dprglist-owner at horta.ncc.com  Fri Jan  9 18:22:03 1998
>Received: from nimon.ncc.com (nimon.ncc.com [199.1.173.2])
>	by horta.ncc.com (8.8.5/8.8.5) with SMTP id SAA07848
>	for <dprglist at horta.ncc.com>; Fri, 9 Jan 1998 18:22:03 -0600
>Received: from kmoravec at usa.net [206.66.12.40] by nimon.ncc.com (OS/2
NCCmail v0.33) with SMTP
>          for dprglist at dprg.org; Fri, 09 Jan 98 17:08:53 CST
>Received: from pent90 from [206.66.14.91] by mail.airmail.net 
>	(/\##/\ Smail3.1.30.16 #30.232) with smtp for <dprglist at dprg.org>
>	id <m0xqniG-0005iWE at mail.airmail.net>; Fri, 9 Jan 98 17:19:40 -0600 (CST)
>Message-ID: <34B6B0AC.2CEF at usa.net>
>Date: Fri, 09 Jan 1998 17:20:12 -0600
>From: Kipton Moravec <kmoravec at usa.net>
>Reply-To: kmoravec at usa.net
>X-Mailer: Mozilla 3.01C-KIT  (WinNT; U)
>MIME-Version: 1.0
>To: dprglist at dprg.org
>Subject: Re: DPRG: Deep Thoughts and rambling
>References: <199801072135.PAA20156 at sun1559.spd.dsccc.com>
<34B65F24.4BE8B2DE at cryogen.com>
>Content-Type: text/plain; charset=us-ascii
>Content-Transfer-Encoding: 7bit
>
>Alan Bredon wrote:
>> 
>> Jim Brown wrote:
>> 
>> > Case 5:
>> > The baby goes near a power socket (want)
>> > Mommy spanks baby (painful deterrant)
>> > Baby cries in pain (reflex action)
>> > maybe happens a few more times and then
>> > the baby learns not to go near the socket (deturred/dislike)
>> 
>> Jim,
>> Your discussion of forms of intelligence and behavior is well thought
>> out.
>> I believe that the first step (want) is an inherent curiosity or a
>> constant stimulus to investigate the environment.
>> This is the part of behavior that may be sort of instinctive and is
>> necessary to start the intelligence gathering process.
>> Without it a being/robot would sit in one place at the
>> refrigerator/charger.
>> 
>
>I agree.  This is one of the things missing in the Little Ricci II
>writeups.  There was no indication of what constituted pain/pleasure. Or
>what was good for the robot to do, or what was bad for it to do.  In all
>learning systems there has to be the feedback, as to the difference
>between a good choice and a bad choice. (Unfortunately, the criminal
>justice has gone away from this and it is a mess, but I digress.)  For
>humans, many many things give us pleasure and many many different things
>give us pain.
>
>For a robot, obvious pain sensors are bumpers (when you hit something it
>is bad), tilt sensors (if you fall over it is really bad), temperature
>sensors, (stay away from fire), etc. But what are pleasure sensors?  It
>can't be don't hit something or don't roll over (or just the opposite of
>the pain sensors)...
>
>Anyone got any ideas about this?
>
>Regards,
>Kip
>
>
>
>
- - - ____ - - - - - - ___ - - - - - - - - - - - - - - - - - - - - - - - - - -
    \/\_\@  ____    /  /\ __  ___          ___    http://www.dprg.org 1-17
    / / /\ / / /\  /--/ //\_\/\_/\ /\/\/\ /\_/\  http://users.why.net/jbrown
/__/ / / // / / / /__/ // / /__/ //_/_/ // // / (972)519-2868, (972)495-3821
\__\/  \/ \/\/\/  \__\/ \/  \__\/ \_\_\/ \/ \/ jgbrown at spdmail.spd.dsccc.com

------------------------------

More information about the DPRG mailing list