I saw a streamer call a procedurally generated level “ai generated” and I wanted to pull my hair out

I think these two fields are very closely related and have some overlap. My favorite procgen algorithm, Wavefuncion Collapse, can be described using the framework of machine learning. It has hyperparameters, it has model parameters, it has training data and it does inference. These are all common aspects of modern “AI” techniques.

I thought “Wavefunction Collapse” is just misnamed Monte Carlo. Where does it use training data?

WFC is a full method of map generation. Monte Carlo is not.

WFC is a full method of map generation. Monte Carlo is not afaik.

MC is a statistical method, it doesn’t have anything to do with map generation. WFC is a form of MC.

To answer your question, the original paper on WFC uses training data, hyperparameters, etc. They took a grid of pixels (training data), scanned it using a kernal of varying size (model parameter), and used that as the basis for the wavefunction probability model. I wouldn’t call it AI though because it doesn’t train or self-improve like ML does.

Could you share the paper? Everything I read about WFC is “you have tiles that are stitched together according to rules with a bit of randomness”, which is literally MC.

I don’t think WFC can be described as an example of a Monte Carlo method.

In a Monte Carlo experiment, you use randomness to approximate a solution, for example to solve an integral where you don’t have a closed form. The more you sample, the more accurate the result.

In WFC, the number of random experiments depends on your map size and is not variable.