can a neural network learn to walk as a physical object in a physics simulation? here I train walking neural nets with an evolutionary algorithm. The input nodes/feet are activated by sine waves at learned phases & connections between two neurons extend based on their difference

aka “embodied neural networks”

Remember soda constructor?

Whatever the result, they seem to be enjoying themselves.

this is amazing. would you consider open-sourcing the code? I'd love to extend this to optimizing the architecture of the net itself, so it ends up having to trade off physical bulk with function approximation power

Looks kinda similar

Surely a CNN will work better because of the strides?

reminds me of this, also controlled by a neural net

How do you think of this stuff??

I saw a cool demo of a neural net controlling an inverted pendulum, and was thinking it would be cool to make a nnet control something. I was also thinking about that old game soda constructor. Then I thought of this idea like a bad joke about learning to walk

You should make it so that the ground is a treadmill with numbers on it, and the fitness function rewards it both for walking and for adding the numbers it's touching correctly.