Procedural Content Generation via Machine Learning

Matthew Guzdial, Ph.D., is an Assistant Professor in the Computing Science department of the University of Alberta and a Canada CIFAR AI Chair at the Alberta Machine Intelligence Institute (Amii). His research focuses on the intersection of machine learning, creativity, and human-centered computing. He is a recipient of an Early Career Researcher Award from NSERC, a Unity Graduate Fellowship, and two best conference paper awards from the International Conference on Computational Creativity. His work has been featured in the BBC, WIRED, Popular Science, and Time.Sam Snodgrass, Ph.D., is the Manager of the Applied AI team at modl.ai, a game AI company focused on bringing state of the art game AI research from academia to the games industry. His research focuses on making PCGML more accessible to non-ML experts. This work includes making PCGML systems more adaptable and self-reliant, reducing the authorial burden of creating training data through domain blending, and building tools that allow for easier interactions with the underlying PCGML systems and their outputs. Through his work at modl.ai he has deployed several mixed-initiative PCGML tools into game studios to assist with level design and creation.Adam Summerville, Ph.D., is the lead AI engineer for Procedural Content Generation at The Molasses Flood, a CD Projekt studio. Prior to this, he was an assistant professor at California State Polytechnic University, Pomona. His research focuses on the intersection of artificial intelligence in games with a high-level goal of enabling experiences that would not be possible without artificial intelligence. This research ranges from procedural generation of levels, social simulation for games, and the use of natural language processing for gameplay. His work has been shown at the SF MoMA, SlamDance, and won the audience choice award at IndieCade.

• Introduction.- Classical PCG.- An Introduction of ML Through PCG.- PCGML Process Overview.- Constraint-based PCGML Approaches.- Probabilistic PCGML Approaches.- Neural Networks – Introduction.- Sequence-based DNN PCGML.- Grid-based DNN PCGML.- Reinforcement Learning PCG.- Generative AI.- Mixed-Initiative PCGML.- Open Problems.- Resources and Conclusions.