Human-Level AI's Killer Application: Interactive Computer Games
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Using heuristics to evaluate the playability of games
CHI '04 Extended Abstracts on Human Factors in Computing Systems
| Hi-index | 0.00 |
Game AI research is moving away from the creation of dominant computer agents to the idea of creating agents that focus on entertainment. The development of a realistic definition of entertainment, or "fun", requires a qualitative measure on subjective assessments from a large, diverse field of participants. We present our work in the early stages of creating a web-based system for testing different opponent behaviors. We have augmented the Link4 game[6] to compete again human players using three different opponent strategies. Human players will rank the entertainment value of these agents, as well as personal information that may affect their ranking. This paper describes the simple behaviors we have coded for testing purposes and the challenge of capturing user the experience while not detracting from it.