Neural network learns how to drive a car on a track. Simple 2D simulation with pyglet & numpy.
nnr.preview.mp4
Warning
This code is a product of my early programming days. I've refactored it, but it might not align with current best practices.
pip install -r requirements.txt
Should work with Python 3.0 and higher.
For example:
py -3.10 .\__main__.py
Or use a virtual environment.
config.json
{
"width": 1280
"height": 720
"friction": 0.1
"render_timestep": 0.025 // time between frames in seconds - 0.025s = 40 FPS
"timeout_seconds": 30 // maximum time for each gen
"population": 40 // number of cars
"mutation_rate": 0.6 // mutation rate after gen
}
default_nn_config.json - Default car config for new saves.
{
"name" : "test"
"acceleration": 1
"friction": 0.95
"max_speed": 30
"rotation_speed": 4
"shape": [6, 4, 3, 2] // neural network shape - do not change first and last layer
"max_score": 0
"gen_count": 0
}
Best cars in each generation are chosen to be the parents of the next, slightly mutated generation.
 |
 |
|---|