Pole Balancer

This is a demonstration of computer-guided pole balancing using a reinforcement learning method called SANE (Symbiotic, Adaptive Neuro-Evolution), which evolves a population of neurons through genetic algorithms to form a neural network capable of performing a task. Symbiotic evolution promotes both cooperation and specialization, which results in a fast, efficient genetic search and discourages convergence to suboptimal solutions.

You need a Java enabled brower to view this example.

Click in the applet window and press spacebar to continue next generation of training, or enter to restart pole in another random state. The left and right arrow keys can be used to disrupt the compueter's balance by forcing the pole a few degrees in that direction.