racing-AI
A hundred cars that cannot see the track, evolving until they can drive it.
The story
I saw a video about evolving controllers by breeding and mutation, and I wanted to see for myself whether something that simple really works. It does. A hundred cars start with random numbers in their heads and drive into a wall.
The few that get furthest are copied, mixed and slightly mutated, and their children try again. Nobody shows them a good lap. There is no dataset and no training in the usual sense, only survival.
The trick is what the car is allowed to see: seven distance readings to the walls and its own speed. It has no map and no idea where it is, so it cannot learn a track by heart. Whatever it ends up doing has to be actual driving.
It is scored on freshly generated tracks every generation, so there is nothing to memorise anyway. After three hundred generations it completes tracks it has never seen, and it brakes before corners, which nothing in the code ever rewarded. It just turned out to be the only way through.
Gallery
Want something like this?
I can build the same thing for your product.
Tell me what you have in mind. You get an answer the same day, with a realistic scope and timeline, not a sales pitch.