.
This video shows the evolution of coordinated behavior of simulated robot soccer players. In the simulation, each soccer player is controlled by a neural network. The neural networks are evolved using an evolutionary algorithm, so generation after generation the strategy improves.
The corresponding paper "Evolving neural network controllers for a team of self-organizing robots" is available at http://www.demesos.tk
I would be lying if I pretended to fully understand what just happened. But I do feel qualified to say that this was an awesome display of artificial intelligence research. Sweet!
Post new comment