I made a neural network learn to dodge bullets, from scratch
I’ve wanted to implement NEAT (NeuroEvolution of Augmenting Topologies) from scratch for a while now. Every tutorial I found online just does pip install neat-python and calls .evolve(), and that felt like cheating myself out of actually understanding it. So I built a small twin-stick space shooter in C++ with raylib, and instead of playing it myself, I let a population of evolving neural networks play it for me. No PyTorch, no gradient descent, no backprop....