Blondie24
From Wikipedia, the free encyclopedia
Blondie24 is an artificial intelligence checkers-playing computer program. The program was named after the screen name used by a team led by David B. Fogel to determine the effectiveness of an artificial intelligence checkers-playing computer program.
The screen name was used on the The Zone, an internet boardgaming site, during 1999. During this time, Blondie24 played against some 165 human opponents and was shown to achieve a rating of 2048, or better than 99.61% of the playing population of that web site.
The design of Blondie24 is based on a minimax algorithm of the checkers game tree in which the evaluation function is an artificial neural network. The neural net receives as input a vector representation of the checkerboard positions and returns a single value which is passed on to the minimax algorithm.
The neural net weightings were obtained by an evolutionary algorithm, in this case by having a population of Blondie24-like programs play against each other and later eliminating those with fewest earned points in which the players earned +1 for a win, 0 for a draw, and -2 for a loss, and repeating the process with a new population derived from the winners. The result was an evolutionary process selecting the programs that played better checkers games.
The significance of the Blondie24 program is that its ability to play checkers did not rely on any human expertise of the game, rather, it came solely from the total points earned by each player and the evolutionary process itself. The evolving players did not even know which individual games ended in a win, loss, or draw.
Fogel, along with his colleague Kumar Chellapila, documented their experiment in several publications (see references). Fogel also authored a book on the development of Blondie24, and the experiences he and his team had while running Blondie24 in on-line checkers games, and eventually in obtaining a victory against Chinook at the "novice" level, which was equivalent to a high-level expert. Chinook at full strength was the leading checkers-playing computer program at the time.
[edit] References
- Chellapilla K and Fogel DB (1999) "Evolution, Neural Networks, Games, and Intelligence," Proc. IEEE, Vol. 87:9, Sept., pp. 1471-1496. (.pdf)
- Chellapilla K and Fogel DB (1999) "Evolving Neural Networks to Play Checkers without Expert Knowledge," IEEE Trans. Neural Networks, Vol. 10:6, pp. 1382-1391. (.pdf)
- Chellapilla K and Fogel DB (2001) “Evolving an Expert Checkers Playing Program without Using Human Expertise,” , IEEE Transactions on Evolutionary Computation, Vol. 5:4, pp.422-428. (.pdf)
- "Blondie24: Playing at the Edge of AI", Fogel DB, (2002) Morgan Kaufmann Publishers, Inc., San Francisco, CA. ISBN 1-55860-783-8
