Ett Oskarpt Beslut : om Oskarp Logik i speldesign

Sammanfattning: This paper examines possible applications of fuzzy logic on the field of artificial intelligence in digital games. It describes fuzzy logic in contrast to crisp logic. The paper will give several examples of possible applications of fuzzy logic-based decision making for game AI. These examples include the choosing of weapons for AI agents and the gas-break decision of an AI-controlled car. The paper will also analyze the impacts of game AI which makes decisions based on many factors. It will detail how transitions between AI states can be made more fluid with fuzzy logic. The paper comes to the conclusion that game AI with decision making based on fuzzy logic and fuzzy sets has several advantages and disadvantages. These advantages include the ability for AI agents to make decisions based on many factors. Disadvantages include the increased complexity inherent in poorly constructed fuzzy logic based AI. This complexity emerges when too many variables are part of the rule description, and each variable has several different states. In these cases, an unmanageable amount of rules will be produced.