How to figure which words?  You don't really want to just leave out certain 
words from the 'simulated 1600-player' vocab, but suppose you had a way of 
assessing the "commonality" of a given word?

There's two factors you could easily obtain as inputs to a probabilistic 
"likelihood of unknownness" function:

1) Number of hits that Google returns for the word (RETINAS:  816,000; 
GESNERIAD:  28,700;  STRONGYL:  3,390).  Downscale this number if the search 
yields a "Did you mean..." hint.

2) Rack probability for 7s and higher, power-tile count for 6s and below.

Compute a value based on these considerations and compare against a 
randomly-generated value.

As for myself, I wouldn't play such a computer opponent, but it might be 
interesting to see the results of research into "artifical stupidity".  In 
fact, 
  there might even be an Ignoble Prize in here somewhere.
--gvc

[EMAIL PROTECTED] wrote:
> We can only guess the playing vocabulary of a top human player, so who 
> knows.  We know that Quackle has a perfect vocabulary-hakim withstanding. 
> 
> So could we guess how much of advantage having a perfect vocabulary 
> would be by simulating Quackle perfect against Quackle not perfect 
> (QNP)?  Would it be possible to load a second dictionary file or have 
> two instances of Quackle play each other?
> 
> A simple scenario would have QNP have a limited vocabulary of all 3, 4, 
> 5's and say 80% of the 6, 7, 8, 9's.  It would never challenge QP...
> 
> Anybody up to this?
> 
> Ron
> 
>       
> 
> 

Reply via email to