Thanks! Share it with your friends!
Teaching a neural network to drive a car. It's a simple network with a fixed number of hidden nodes (no NEAT), and no bias. Yet it manages to drive the cars fast and safe after just a few generations. Population is 650. The network evolves through random mutation (no cross-breeding). Fitness evaluation is currently done manually as explained in the video.
Car picture by Unlucky Studio:
Track background created by Keely for Quickrally and modified a bit:
Background music by Trevor Lentz:
Coding by Johan Eliasson in 2019.