Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!think.com!mintaka!yale!quasi-eli!cs.yale.edu!blenko-tom
From: blenko-tom@cs.yale.edu (Tom Blenko)
Newsgroups: comp.ai.neural-nets
Subject: Re: Learning to play a game  (was Re: Chip vs Chess Master)
Keywords: Games, chess
Message-ID: <30106@cs.yale.edu>
Date: 16 Apr 91 16:55:56 GMT
References: <31403@usc> <pluto.670117666@zaius> <1356@anaxagoras.ils.nwu.edu>
Sender: news@cs.yale.edu
Distribution: comp
Organization: Yale University Computer Science Dept., New Haven, CT 06520-2158
Lines: 20
Nntp-Posting-Host: morphism.systemsz.cs.yale.edu
Originator: blenko@morphism.CS.Yale.Edu

In article <1356@anaxagoras.ils.nwu.edu> krulwich@ils.nwu.edu (Bruce Krulwich) writes:
|Don't get me wrong -- NeuroGammon is a good piece of network engineering, and
|it's very interesting that the network (without any projection) was able to
|play expert-level backgammon.  I'm merely objecting to the claim that it
|learned the concepts necessary to play.  If Tesauro did a later version than I
|saw which did this, I retract this message, but everything I've seen has the
|features preselected, which avoids all the hard issues in machine learning.

Perhaps you're just speaking casually here, but that seems
inappropriate when you are mounting such a criticism.

Certainly some of the features are pre-selected (or "built-in").  Is it
possible to have a system in which this isn't true? I think not.

Since each element of this system learns what to "do next", given some
history of what has transpired previously, and it IS able to win
backgammon matches, why ever wouldn't one say that it has learned the
concepts necessary to play?

	Tom