Neuroevolution Racing Lab

A population of neural networks starts out knowing nothing. The ones that get furthest survive and breed. Nobody tells them what a corner is.

training Grand Prix
generation 1
0 / 0 alive
1

Sense

Seven rays measure the distance to the nearest wall, plus the car's own speed. That's the entire input eight numbers. No map, no racing line, no idea where the finish is.

2

Decide

Those numbers run through a small feed-forward network and come out as two values: how hard to steer, and how hard to accelerate or brake. That network is the policy.

3

Score

Reward comes from passing gates in order, with a small bonus for carrying speed and a penalty for hitting a wall. It is deliberately sparse nothing tells the car how to corner.

4

Select

The whole generation dies, the best few are copied unchanged, and the rest are rebuilt by mixing two good parents and randomly nudging the weights. Repeat.