What is Tron?

An experiment in Online Machine Learning

With every mistake we must surely be learning

G. Harrison

Genetic Programming

Genetic programming is a computer learning method that imitates nature's selection process to lead a population of computer programs towards improving levels of performance.

Tron

Tron is a dynamic game, difficult for computers to learn. Playing against itself a computer might believe that is doing a good job when it is not, because it lacks a parameter (ie, a really good player) to compare.

This experiment

In this experiment, we have put a genetic learning algorithm online. A "background" GA generates players by having the computer play itself. A "foreground" GA leads the evolutionary process, evaluating players by their performance against real people.

Your participation

Every time you play a game you incorporate a new tiny bit of information into our genetic algorithm. Hopefully, in the following few months, the computer may come up with smarter opponents than it had in the beginning.

Slide Show

• Click here To go over our presentation of this project at the SAB'98 conference , August 21, 1998 at the University of Zurich.
  NEW RESULTS presented at SAB'00, September 15, 2000, at the Collège de France in Paris.

Publications about this project

• Funes, Pablo and Pollack, Jordan B. (2000). Measuring Progress in Coevolutionary Competition.
  From Animals to Animats 6: Proceedings of the Sixth International Conference on the Simulation of Adaptive Behavior. MIT Press.

• Sklar, Elizabeth, Blair, Alan D. , Funes, Pablo and Pollack, Jordan (1999). Training Intelligent Agents using Human Internet Data .
  IAT-99. (to appear).

• Funes, P., Sklar, E., Juillé, H. and Pollack, J. (1998). Animal-Animat Coevolution: Using the Animal Population as Fitness Function.
  Pfeifer, R. et. al. (eds.) From Animals to Animats 5: Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior . MIT Press. pp 525-533.

• Blair, Alan D. , Sklar, Elizabeth and Funes, Pablo (1998). Co-evolution, Determinism and Robustness.
  In Simulated Evolution and Learning (SEAL-98). Lecture Notes in Artificial Intelligence 1585. Bob McKay, Xin Yao, Charles S. Newton, Jong-Hwan Kim, Takeshi Furahashi, eds., Springer-Verlag.

• Funes, P., Sklar, E., Juillé, H. and Pollack, J. (1997). The Internet as a Virtual Ecology: Coevolutionary Arms Races Between Human and Artificial Populations.
  Brandeis University Computer Science Technical Report CS-97-197.