checkers

[David Mechner <mechner@xxxxxxxxxxxxxxxxx>]

Sounds like Arthur Samuel's checkers program. The description isn't
quite right, and it didn't just do rote learning - it adjusted
coefficients of an evaluation function. And the program became a good
player, but it certainly wasn't unbeatable. 

Check out:
http://www-anw.cs.umass.edu/~rich/book/11/node3.html

for a description and references. 

-David

-- 
David A. Mechner            Center for Neural Science
mechner@xxxxxxxxxxxxxxxxx         4 Washington Place, New York, NY 10003
212.998.3580                http://www.cns.nyu.edu/~mechner/


Jill Irving wrote:
> On May 29,  8:31am, keith reid-green wrote:
> > Subject: [CM>] CM> Checkers
> > In the 1950s somebody (at IBM?) wrote a checkers program that was
> > self-learning.  He programmed the computer's moves only to follow 
> > the rules of checkers--no intelligence in the computer program, 
> > except that when the machine lost a game, it retained all the 
> > board positions for that game and tried not to replicate any 
> > of them in subsequent games.  The author claimed that after 
> > about 15 games the computer won one, lost the next two and was
> > unbeatable thereafter.
 . . .
> > I would like to read a primary source description of this early 
> > machine intelligence experiment.  Can anybody cite the source
> > material, or better yet, send me a copy?
> >
> > Keith