Xref: utzoo rec.games.misc:15281 comp.ai:8903
Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!wuarchive!zaphod.mps.ohio-state.edu!samsung!munnari.oz.au!yoyo.aarnet.edu.au!sirius.ucs.adelaide.edu.au!levels!marwk
From: marwk@levels.sait.edu.au
Newsgroups: rec.games.misc,comp.ai
Subject: How do games learn? (was  Re: looking for name of a game)
Message-ID: <16087.27f874ec@levels.sait.edu.au>
Date: 2 Apr 91 02:41:23 GMT
References: <91090.130516ASNXS@ASUACAD.BITNET> <1991Apr1.130740.19670@IDA.ORG>
Organization: University of South Australia
Lines: 20

> Go-moku or Runjyu
> -----------------
> Another comment:  In 1961 I wrote a playing/learning program (based on
> Samuel's Checker-learning method) for this game.  It (almost) ran on a
> computer now known as UNIVAC I but then known a THE UNIVAC.
>
> --Dick Wexelblat  (rlw@ida.org) 703 845 6601

How can one write a program that learns?  I do not see how.

One has parameters in the heuristic evaluation functions, so how can these
change based on experience?

Thanks.
Ray
--
University of South Australia   | Plus ca change, plus c'est la meme chose.
P.O. Box 1                      | Ghing thien me how, ming thien gung me how.
Ingle Farm                      | Knobs, knobs everywhere,
South Australia                 |              just vary a knob to think!