1. Capturing Player Enjoyment in Computer Games

The current state-of-the-art in intelligent game design using Artificial Intelligence (AI) techniques is mainly focused on generating human-like and intelligent characters. Even though complex opponent behaviors emerge through various machine learning techniques, there is generally no further analysis of whether these behaviors contribute to the satisfaction of the player . The implicit hypothesis motivating this research is that intelligent opponent behaviors enable the player to gain more satisfaction from the game. This hypothesis may well be true; however, since no notion of entertainment or enjoyment is explicitly defined, there is therefore no evidence that a specific opponent behavior generates enjoyable games. This chapter introduces a discussion of quantitative entertainment capture in real-time and presents two dissimilar approaches for modeling player satisfaction. Successfully capturing the level of entertainment during play provides insights for designing the appropriate AI methodology for entertainment augmentation in real-time. For this purpose, adaptive on-line learning methodologies are proposed and their strengths and limitations are discussed.