Newsgroups: comp.ai.games
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!swrinde!news.dell.com!tadpole.com!uunet!in1.uu.net!psinntp!nntp.hk.super.net!news.ust.hk!pmchoi
From: pmchoi@cs.ust.hk (Sam P. M. Choi)
Subject: Re: neural nets for backgammon
Message-ID: <1995Mar15.141503.13498@uxmail.ust.hk>
Sender: usenet@uxmail.ust.hk (usenet account)
Nntp-Posting-Host: cssu40.cs.ust.hk
Organization: The Hong Kong University of Science and Technology
X-Newsreader: TIN [version 1.2 PL2]
References: <D5Foqn.E7C@news.cern.ch>
Date: Wed, 15 Mar 1995 14:15:03 GMT
Lines: 27

owen ransen (ransen@cerncs2.cern.ch) wrote:

: I read in Dr.Dobbs about a year ago about a neural network
: program which learned on it's own how to play backgammon.
: I have tried myself to adapt a "statistical" backgammon
: program to a C++ neurla network system but with abysmal results:
: The stats version of the program easily beat the NN version of
: the program.
: Does anywone know who wrote the NN version metioned in Dr.Dobbs?
: And are the sources freely available?
: Thanx,
: Owen

I think you are talking about TD-gammon written by Tesauro. You 
can get more information from the following paper:

Tesauro, G. (1994). TD-Gammon, a self-teaching backgammon program,
achieves master-level play. Neural Computation, 6(2), 215-219.

--

,----------------------------v-------------------------.
|  Sam P. M. Choi            |  pmchoi@cs.ust.hk       |
|  Dept of Computer Science  |  Tel: (852)358-8838     |
|  HKUST, Clear Water Bay    |  Fax: (852)358-1477     |
|  Hong Kong                 |                         |
`----------------------------^-------------------------'
