I'd love to research practical ways to apply modern machine learning techniques to video games. Video game AI techniques seem stuck in the 90s. Too many games have been limited by poor AI, and I want to fix that.
I'm currently wanting to study bandit methods and tabular reinforcent learning. These are limited, but simple and predictable, which is important for games.
I'm currently wanting to study bandit methods and tabular reinforcent learning. These are limited, but simple and predictable, which is important for games.