bug-gnubg
[Top][All Lists]
Advanced

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

Re: [Bug-gnubg] How fast can you cheat??


From: Michael Petch
Subject: Re: [Bug-gnubg] How fast can you cheat??
Date: Fri, 21 Aug 2009 14:13:00 -0600
User-agent: Microsoft-Entourage/12.20.0.090605



On 21/08/09 11:37 AM, "Frank Berger" <address@hidden> wrote:

> This is absolute nonsens.
> Why? quite easy. Any NN I'm aware of is presented the position to
> evaluate it.
> Therefore it never sees the dice and can therefore not learn a pattern.
> 

I agree and disagree. The NN never sees the dice - agreed. However  I
believe an NN is indirectly guided by the dice. If you took the neural net
trainer and had Gnubg play itself again but this time set up the random
number source to throw away all the doubles I am pretty sure how the Bot
learns to play the game over time will change.

My opinion though is the Mersenne Twister is cryptographically strong enough
and has such a massive period that the Bot would likely not be able to see
anything (the period for standard 32 bit versions of mersenne are 2^219937 ?
1).

On a side note if one reviews the code from the old days, Mersenne Twister
was not available (Unimplemented) and the random data source could have also
been something with a considerable shorter period.

If you trained with one random number generator and then play with another
any thing the NN might have learned as a result doesn't matter. GnuBG
doesn't continue to learn while it plays humans (or have knwoledge of the
generator being used during the actual match), so it can't possible garner
knowledge from random number generators it may  never have seen (or were
implemented differently).

I have read most of Roy's online postings, and his website and authoring
pages. His view on Gnubg is that it is self learning and changes as it plays
an opponent. This is his single biggest false assumption. He asked Albert
Silver in 2006 if the assumption that Gnubg learns during a match was
correct. I believe since then Roy has continued to believe that the bot
continues to learn, although he's been told the contrary.







reply via email to

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