Player Modeling via Multi-Armed Bandits
This addresses the challenge of expensive user studies in adaptive games by enabling pre-evaluation of algorithms, though it is incremental in applying known methods to a specific domain.
The paper tackles the problem of building personalized player models from behavior in adaptive games, presenting a multi-armed bandit approach that simultaneously collects data and adapts the experience, with evaluation showing empirical results from simulations and real players.
This paper focuses on building personalized player models solely from player behavior in the context of adaptive games. We present two main contributions: The first is a novel approach to player modeling based on multi-armed bandits (MABs). This approach addresses, at the same time and in a principled way, both the problem of collecting data to model the characteristics of interest for the current player and the problem of adapting the interactive experience based on this model. Second, we present an approach to evaluating and fine-tuning these algorithms prior to generating data in a user study. This is an important problem, because conducting user studies is an expensive and labor-intensive process; therefore, an ability to evaluate the algorithms beforehand can save a significant amount of resources. We evaluate our approach in the context of modeling players' social comparison orientation (SCO) and present empirical results from both simulations and real players.