Predicting Game Difficulty and Engagement Using AI Players

Loading...
Thumbnail Image
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
Date
2021-09
Major/Subject
Mcode
Degree programme
Language
en
Pages
17
1-17
Series
Proceedings of the ACM on Human-Computer Interaction, Volume 5, issue CHI PLAY
Abstract
This paper presents a novel approach to automated playtesting for the prediction of human player behavior and experience. We have previously demonstrated that Deep Reinforcement Learning (DRL) game-playing agents can predict both game difficulty and player engagement, operationalized as average pass and churn rates. We improve this approach by enhancing DRL with Monte Carlo Tree Search (MCTS). We also motivate an enhanced selection strategy for predictor features, based on the observation that an AI agent's best-case performance can yield stronger correlations with human data than the agent's average performance. Both additions consistently improve the prediction accuracy, and the DRL-enhanced MCTS outperforms both DRL and vanilla MCTS in the hardest levels. We conclude that player modelling via automated playtesting can benefit from combining DRL and MCTS. Moreover, it can be worthwhile to investigate a subset of repeated best AI agent runs, if AI gameplay does not yield good predictions on average.
Description
Keywords
Other note
Citation
Roohi, S, Guckelsberger, C, Relas, A, Heiskanen, H, Takatalo, J & Hämäläinen, P 2021, ' Predicting Game Difficulty and Engagement Using AI Players ', Proceedings of the ACM on Human-Computer Interaction, vol. 5, no. CHIPLAY, 231, pp. 1-17 . https://doi.org/10.1145/3474658