[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

How about docs on gnubg's net engine? (it cheats!) {wa: Re: [ Bug-gnubg

From: Roy A. Crabtree
Subject: How about docs on gnubg's net engine? (it cheats!) {wa: Re: [ Bug-gnubg] Searching for "BKG—A Program that Plays Backgammon"
Date: Fri, 15 Sep 2006 12:18:41 -0400

You must be an antiquarian like me, to recall such ancient information processing techniques ...


As a side kvetch: Iws looking on gnubg's site for refs to the internal NNP engine, did not see them.

Is this only in the code, or is there a white paper somewere I was too blind to see?

By the way, the engine (more correctly, the learn-ed net) us much more clever than you may think:

It has succesfully "hidden" the several ways it "misleads" players into traps, including "cheating"***:

   It plays the _players_ as much as it plays the _game_.  It uses the players "tells":

       game strategy shifts based on conistently flawed playing.

             Second kvetch: Am I incorrect in assuminhg that the net is not locked during successive plays?
                  That it learns in the current match as well?

                 (There is an outside posibility i Have a viral trap catching the dice throws covertly)

                 (Please note: since the game in fact has an option to throw the best to worst roll for each player,
                   this is a much easier viral hack than you might think).

    If you look carefully, and think a while, then follow the pattern it has, you can esily see it.

             If you understand signal theory (event/condition/timing/cascade), it will pip (sic: pop) out at you.

*** The code is scrupulously clean; nonetheless,
     when a naive player says it (gnubg) cheats,
     it (the neural net) does.


On 9/15/06, Albert Silver <address@hidden> wrote:
Offhand I can think of a number of ways to get it:


You could also contact ICGA, of which Levy is president, and see if it
was printed in some back issue and if so the cost of a reprint/copy.
Or ask ICGA where it could be found outside of the book.

If you know of a magazine where it was printed, you can find one of
several reprint services that are available on the internet, or you
can contact a major library that carries the magazine, such as the NY
Public library, have them copy it, and send it (for a fee). This is a
standard service.

Finally, you could try locating Berliner himself, presuming he isn't dead yet


On 9/15/06, Joachim Matussek <address@hidden > wrote:
> Hello,
> i am searching for an article written by Hans Berliner in 1977 and reprinted in David Levy's "Computer Games I" in 1988.
> "BKG—A Program that Plays Backgammon". Hans Berliner. Computer Science Department Technical Report, Carnegie Mellon University, Pittsburgh, PA, 1977. Reprinted in Computer Games I, (Ed.) David Levy, Springer-Verlag, New York, 1988, pp. 3–28.
> I have no idea where to find this one. Maybe someone can help me.
> Thanks in advance,
> Joachim Matussek
> _______________________________________________
> Bug-gnubg mailing list
> address@hidden
> http://lists.gnu.org/mailman/listinfo/bug-gnubg

Bug-gnubg mailing list

Roy A. Crabtree
UNC '76 gaa.lifer#11086
Room 207 Studio Plus
123 East McCullough Drive
Charlotte, NC 28262-3306
336-340-1304 (office/home/cell/vmail)
704-510-0108x7404 (voicemail residence)


(Copyright) Roy Andrew Crabtree/In Perpetuity
    All Rights/Reserved Explicitly
    Public Reuse Only
    Profits Always Safe Traded
reply via email to

[Prev in Thread] Current Thread [Next in Thread]