Matthew Guzdial

Game engine learning from video

Intelligent agents need to be able to make predictions about their environment. In this work we present a novel approach to learn a forward simulation model via simple search over pixel input. We make use of a video game, Super Mario Bros., as an initial test of our approach as it represents a physics system that is significantly less complex than reality. We demonstrate the significant improvement of our approach in predicting future states compared with a baseline CNN and apply the learned model to train a game playing agent. Thus we evaluate the algorithm in terms of the accuracy and value of its output model.

Deep convolutional player modeling on log and level data

We present a novel approach to player modeling based on a convolutional neural net trained on game event logs. We test our approach and a hybrid extension over two distinct games, a clone of Super Mario Bros. and Gwario, a human computation version of Super Mario Bros.: The Lost Levels. We demonstrate high accuracy in predicting a variety of measures of player experience across these two games. Further we present evidence that our technique derives quality design knowledge and demonstrate the ability to build a more general model.