Player Modeling via Multi-Armed Bandits

Robert C. Gray, Jichen Zhu, Danielle Arigo, Evan Forman, Santiago Ontañón

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Scopus citations


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.

Original languageEnglish (US)
Title of host publicationProceedings of the 15th International Conference on the Foundations of Digital Games, FDG 2020
EditorsGeorgios N. Yannakakis, Antonios Liapis, Kyburz Penny, Vanessa Volz, Foaad Khosmood, Phil Lopes
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450388078
StatePublished - Sep 15 2020
Event15th International Conference on the Foundations of Digital Games, FDG 2020 - Bugibba, Malta
Duration: Sep 15 2020Sep 18 2020

Publication series

NameACM International Conference Proceeding Series


Conference15th International Conference on the Foundations of Digital Games, FDG 2020

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications


Dive into the research topics of 'Player Modeling via Multi-Armed Bandits'. Together they form a unique fingerprint.

Cite this