Player-centered game AI from a flow perspective: Towards a better understanding of past trends and future directions

- We performed an analysis on approaches aimed to adapt the flow to a game AI context.
- We defined a generic framework of flow for game AI (FlowAI).
- From the FlowAI framework standpoint, we proceed to survey the game AI area.
- This survey overviews current trends and challenges in each game AI subarea.
- We identify desirable features to design effective modules for flow based games.

Player-centered approaches that aim to maximize player enjoyment have been steady, but with poor heuristics that do not rely on any particular theory of entertainment. Certainly, the Theory of Flow is the most referred in the game AI area and, still, it is unclear how to effectively design and implement adaptive game modules or understanding which game features drive players to a flow state. Therefore, in this document we perform a systematic analysis of literature aimed to enhance our knowledge about how to adapt flow heuristics to a video game context. This analysis endows us with the knowledge needed to define a flow framework for game AI. Our framework, FlowAI, describes which modules and what gameplay features can be adapted to design an effective video game intended to facilitate the achievement of flow in players. Furthermore, from our framework standpoint, we identify and review existing work that could be adjusted to foster flow. Our aim with this analysis is to identify current challenges, and motivate new directions in the player-centered research area.

111