Player-Centered AI for Automatic Game Personalization: Open Problems

Game personalization research must transition from a system-centered focus on algorithmic complexity toward a player-centered framework that prioritizes individual cognitive processes and user needs. By applying Don Norman’s structure of actions to the gaming domain, the field can better address the psychological requirements of players while maintaining the integrity of game design. This shift is essential for resolving the paradox of personalization, where the desire for adaptive experiences often conflicts with the need to preserve player agency and authorial intent.

The primary obstacles to achieving effective personalization involve reconciling data-driven modeling with theoretical psychological frameworks. Current technical challenges include improving the accuracy of player models, managing procedural content generation, and ensuring that AI-driven adaptations remain transparent. When players cannot form accurate mental models of how a system functions, the resulting personalization often feels intrusive or arbitrary. Consequently, the industry must address the difficulty of designing meaningful, unbiased choices that respect the diverse and often co-existing preferences of individual users.

Advancing this field requires a fundamental shift in methodology, moving away from isolated technical development toward deep, interdisciplinary collaboration between AI researchers and game designers. Future progress depends on creating systems that balance sophisticated machine learning with human-centric experience design. By focusing on these eight identified open problems—ranging from modeling accuracy to the ethical implications of adaptive systems—the industry can move toward more cohesive, responsive, and engaging gaming environments that genuinely reflect the player’s internal state and long-term goals.