Player Modeling via Multi-Armed Bandits

TL;DR

This paper introduces a novel multi-armed bandit approach for personalized player modeling in adaptive games, enabling data collection and experience adaptation, with an evaluation method that reduces the need for costly user studies.

Contribution

The paper presents a new MAB-based method for player modeling and a pre-study evaluation approach to optimize algorithms before user testing.

Findings

Effective modeling of social comparison orientation (SCO)

Successful simulation and real-player validation

Resource-efficient algorithm evaluation

Abstract

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.