Recognizing Player Goals in Open-Ended Digital Games with Markov Logic Networks

In digital games goal recognition centers on identifying the concrete objectives that a player is attempting identifying the concrete objectives that a player is attempting to achieve given a domain model and a sequence of actions in a virtual environment. Goal-recognition models in open-ended digital games introduce opportunities for adapting gameplay events based on the choices of individual players, as well as interpreting player behaviors during post hoc data mining analyses. However, goal recognition in open-ended games poses significant computational challenges, including inherent uncertainty, exploratory actions, and ill-defined goals. This chapter reports on an investigation of Markov logic networks (MLNs) for recognizing player goals in open-ended digital game environments with exploratory actions. The goal-recognition model was trained on a corpus collected from player interactions with an open-ended game-based learning environment known as C rystal I sland . We present experimental results, in which the goal-recognition model was compared to n -gram models. The findings suggest the proposed goal-recognition model yields significant accuracy gains beyond the n -gram models for predicting player goals in an open-ended digital game.