Computer Dice

Forum Archive : Computer Dice

Does MonteCarlo cheat?

From:   Matt Reklaitis
Date:   1 June 1998
Subject:   Re: Why do we THINK that bots cheat?

> What about MonteCarlo?  MC seems to get the ideal roll (you know the
> drill:  making an indirect shot off the bar against a 5-point board,
> rolling boxcars just when needed to win a race or escape from a
> near-prime, etc.) nearly as often as JF or yabs, yet otherwise plays
> at a level (and rating) about as mediocre as my own.  MC's luck seems
> much better evidence of bot cheating than that of the higher ranking
> bots.
> Of course, the high ranking bots could get their ranking by cheating
> too; but my point is that, in Monte Carlo's case, the overabundance
> of lucky rolls is not likely to be due to brilliant play in setting
> up opportunities.
> What do y'all think?


    I am the author of MonteCarlo, and I can assure you that it does not
cheat.  (How can I make it cheat even if I wanted it to?  Its just
another player as far as FIBS is concerned).

    I think part of the reason it seems to win more than it should is
because it makes plays which are obviously wrong, particularly when
bearing off against contact.  I would say that humans tend to become
good players along a different path than a neural net does.  With just a
little experience, a human learns how to bear off safely.  So when
playing aginst another human, if you notice them making "beginner"
mistakes in the bear off you may make some assumptions about their level
of play.  Losing to a player who you think isn't as sharp as you is
usually attributed to their getting lucky.

    These assumptions aren't valid against a computer player.  In technical
positions, humans can select the best play even when the difference
amongst the candidate moves is very small.  Neural nets tend to have
difficulty selecting THE best play in these types of positions.  (But,
atleast the cost of the error is minimal. )  When a neural net makes a
mistake in these positions, its easy to assume that they are missing
some key understanding of the game, then make assumptions about their
skill, followed by the feeling that they got lucky when they win.

    But, think about this:  If the neural nets are making obvious mistakes
in some situations, then they must be making up for it by superior play
in other positions.  The positional play of the neural net is usually
stronger than it seems.  I think this is because its easy for humans to
think there's not much difference between 2 plays when really there is.
So a good positional play by a bot is likely to go unnoticed.

    I'd say a good way to characterize a neural net is that its play is a
sequence of small errors, as opposed to human play, which is a sequence
of correct plays with large blunders scattered about.  The difference
between a good human and a good bot is that the good human will rarely
make technical mistakes but a good bot commonly will. So a human is
better able to convince you of their mastery of the game.

Matt Reklaitis
(Author of MonteCarlo)
Did you find the information in this article useful?          

Do you have any comments you'd like to add?     


Computer Dice

Dice on backgammon servers  (Hank Youngerman, July 2001) 
Does Agushak Backgammon cheat?  (Mr Nabutovsky, June 2000) 
Does BG by George cheat?  (George Sutty, Nov 1995) 
Does Backgammon NJ cheat?  (Greg+, June 2010) 
Does Cybergammon cheat?  (Goto Informatique, Aug 1996) 
Does David's Backgammon cheat?  (Joseph B. Calderone, June 1998) 
Does GNU Backgammon cheat?  (Robert-Jan Veldhuizen, Nov 2002) 
Does Gammontool cheat?  (Jim Hurley, Sept 1991) 
Does Hyper-Gammon cheat?  (ZZyzx, June 1996) 
Does Jellyfish cheat?  (Fredrik Dahl, June 1997) 
Does MVP Backgammon cheat?  (Mark Betz, Oct 1996) 
Does MonteCarlo cheat?  (Matt Reklaitis, June 1998) 
Does Motif cheat?  (Rick Kiesau+, Mar 2004)  [Long message]
Does Motif cheat?  (Billie Patterson, Feb 2003) 
Does Motif cheat?  (Robert D. Johnson, Oct 1996) 
Does Snowie cheat?  (André Nicoulin, Sept 1998) 
Does TD-Gammon cheat?  (Gerry Tesauro, Feb 1997) 
Error rates with computer dice  (NoChinDeluxe+, Feb 2011) 
FIBS: Analysis of 10 million rolls  (Stephen Turner, Apr 1997)  [Recommended reading]
FIBS: Are the dice biased?  (Kit Woolsey, Oct 1996) 
FIBS: Entering from the bar  (Tom Keith+, Apr 1997) 
GamesGrid: Too many jokers?  (Gregg Cattanach, Sept 2001) 
GridGammon: Are the dice random?  (leobueno+, Sept 2011) 
Jellyfish: How to check the dice  (John Goodwin, May 1998)  [Recommended reading]
Jellyfish: Proof it doesn't cheat  (Gary Wong, July 1998) 
MSN Zone: Security flaw  (happyjuggler0, June 2004) 
Official complaint form  (Gary Wong, June 1998)  [Recommended reading]
Randomness testing  (Brett Meyer+, Dec 2010) 
Safe Harbor Games dice  (Michael Petch+, Aug 2011) 
Synopsis of "cheating" postings  (Ray Karmo, Feb 2002) 
Testing for bias  (Kit Woolsey, Jan 1995) 
The dice sure seem unfair!  (Michael Sullivan, Apr 2004) 
Too many repeated rolls?  (Stephen Turner, Mar 1994) 
Winning and losing streaks  (Daniel Murphy, Mar 1998) 

[GammOnLine forum]  From GammOnLine       [Long message]  Long message       [Recommended reading]  Recommended reading       [Recent addition]  Recent addition

  Book Suggestions
Computer Dice
Cube Handling
Cube Handling in Races
Extreme Gammon
Fun and frustration
GNU Backgammon
Luck versus Skill
Magazines & E-zines
Match Archives
Match Equities
Match Play
Match Play at 2-away/2-away
Opening Rolls
Pip Counting
Play Sites
Probability and Statistics
Source Code
Strategy--Bearing Off
Strategy--Checker play


Return to:  Backgammon Galore : Forum Archive Main Page