Motocross and Artificial Neural Networks

In this paper, we investigate training artificial neural networks to ride simulated motorbikes in a new computer game using two different training techniques, Evolutionary Algorithms and the Backpropagation Algorithm. We show that the backpropagation algorithm creates a rider which is faster than that created by the evolutionary algorithm but at the price of requiring a training set created by a human playing the game. Also the evolutionary algorithm has the advantage that it can find solutions which no human has previously found. Both methods create human-like performance in the motocross game.