Fun as Moderate Divergence: Evaluating Experience-Driven PCG via RL

Ziqi WANG, Yuchen LI, Haocheng DU, Jialin LIU*, Georgios N. YANNAKAKIS

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

Abstract

The computational modelling of player experience is key to the generation of personalised game content. The notion of fun, as one of the most peculiar and core aspects of game experience, has often been modelled and quantified for the purpose of content generation with varying success. Recently, measures of a player's fun have been ad-hoc designed to model moderate levels of in-game divergence in platformer games, inspired by Koster's theory of fun. Such measures have shaped the reward functions of game content generative methods following the experience-driven procedural content generation via reinforcement learning (EDRL) paradigm in Super Mario Bros. In this paper, we present a comprehensive user study involving over 90 participants with a dual purpose: to evaluate the ad-hoc fun metrics introduced in the literature and test the effectiveness of the EDRL framework to generate personalised fun Super Mario Bros experiences in an online fashion. Our key findings suggest that moderate degrees of game level and gameplay divergence are highly consistent with the perceived notion of fun of our participants, cross-verifying the ad-hoc designed fun metrics. On the other hand, it appears that EDRL generators manage to match the preferred (i.e., fun) game experiences of each persona, only in part and for some players. Our findings suggest that the use of multi-faceted in-game data, such as events and actions, will likely enable the modelling of more nuanced gameplay behaviours. Additionally, the verification of player persona modelling and the enhancement of player engagement through dynamic experience modelling are suggested as potential future directions.

Original languageEnglish
Number of pages14
JournalIEEE Transactions on Games
Early online date9 Sept 2024
DOIs
Publication statusE-pub ahead of print - 9 Sept 2024
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

Funding

This work was supported by the National Key R&D Program of China (Grant No. 2023YFE0106300), the National Natural Science Foundation of China (Grant No. 62250710682), the Shenzhen Science and Technology Program (Grant No. 20220815181327001), the Guangdong Major Project of Basic and Applied Basic Research (Grant No. 2023B0303000010), the Guangdong Provincial Key Laboratory (Grant No. 2020B121201001), and the Research Institute of Trustworthy Autonomous Systems.

Keywords

  • Experience modelling
  • platformer games
  • procedural content generation
  • Super Mario Bros
  • user study

Fingerprint

Dive into the research topics of 'Fun as Moderate Divergence: Evaluating Experience-Driven PCG via RL'. Together they form a unique fingerprint.

Cite this