Difficulty Modelling in Puzzle Games

Publikation: Artikel i tidsskrift og konference artikel i tidsskriftTidsskriftartikelForskningpeer review

Abstrakt

Difficulty is one of the key drivers of player engagement and it is often one of the aspects that designers tweak most to optimise the player experience; operationalising it is, therefore, a crucial task for game development studios.
A common practice consists in creating metrics out of data collected by player interactions with the content; however, this allows estimation only after the content release and does not consider the characteristics of potential future players.
In this article, we present a number of potential solutions for the estimation of difficulty under such conditions, and we showcase the results of a comparative study intended to understand which method and which types of data that perform better in different scenarios.
The results reveal that models that are trained on a combination of cohort statistics and simulated data produce the most accurate estimations of difficulty across all scenarios. Furthermore, among these models, artificial neural networks show the most consistent results.
OriginalsprogEngelsk
TidsskriftIEEE Transactions on Games
StatusAfsendt - 2022

Citationsformater