Project · 2020

Deep Player Behavior Models

A project on developing deep player behavior models for dynamic and generative non-player character interactions, game testing, player substitution and fraud detection.

This is a project on developing deep player behavior models for dynamic and generative non-player character interactions, game testing, player substitution and fraud detection. DPBM is a collaboration led by Johannes Pfau at the TZI Digital Media Lab at the University of Bremen in Germany and represents key outputs from his PhD.

Please see an exemplary video drawn from the publication “Enemy Within: Long-term motivation effects of deep player behavior models for dynamic difficulty adjustment” below:

Please take a look at the publications listed below for further details and some associated videos.

Related publications

Bot or not? User Perceptions of Player Substitution with Deep Player Behavior Models

J. Pfau, J. David Smeddinck, I. Bikas, R. Malaka · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

Enemy Within: Long-term Motivation Effects of Deep Player Behavior Models for Dynamic Difficulty Adjustment

J. Pfau, J. David Smeddinck, R. Malaka · _Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

The Case for Usable AI: What Industry Professionals Make of Academic AI in Video Games

J. Pfau, J. David Smeddinck, R. Malaka · _Extended Abstracts of the 2020 Annual Symposium on Computer-Human Interaction in Play

Deep Player Behavior Models: Evaluating a Novel Take on Dynamic Difficulty Adjustment

J. Pfau, J. David Smeddinck, R. Malaka · Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems

Towards Deep Player Behavior Models in MMORPGs

J. Pfau, J. David Smeddinck, R. Malaka · CHI PLAY ‘18 Proceedings of the 2018 Annual Symposium on Computer-Human Interaction in Play