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

The computational modeling of player experience is key to the generation of personalized game content. The notion of fun, as one of the most peculiar and core aspects of game experience, has often been modeled 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 article, 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 personalized 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 multifaceted in-game data, such as events and actions, will likely enable the modeling of more nuanced gameplay behaviors. In addition, the verification of player persona modeling and the enhancement of player engagement through dynamic experience modelling are suggested as potential future directions.