View, browse and sort the ever-growing list of GDC sessions by pass type, track, format, and more! With Session Scheduler, create an account to build your own GDC schedule and access it anywhere, including on the GDC app, once live.
If you've registered for GDC, you can use the same login credentials. Adding a session to your schedule does not guarantee you a seat. Sessions do fill up, so please arrive early to sessions that you would like to attend.
Daiki Satoi (AI Researcher, Square Enix Co., Ltd.)
Yuta Mizuno (AI Technical Game Designer, Square Enix Co., Ltd.)
Location: Room 2002, West Hall
Date: Tuesday, March 19
Time: 2:10pm - 2:40pm
Pass Type: All Access, GDC Conference + Summits, GDC Summits - Get your pass now!
Topic: AI Summit
Vault Recording: Video
Audience Level: All
Some games have explored dynamically controlled gameplay-related systems and proposed interesting Meta AI designs. There is a lack of discrimination regarding user’s possible mental states: feeling “relaxed” is different from “bored” and each case should be processed differently. Game AI can benefit from more generic architectures and emotion-based Meta AI.
Yuta Mizuno and Daiki Satoi from Square Enix will discuss general Meta AI design and 2D Emotion Map based Meta AI. General Meta AI design will focus on the “Rule-Interaction-Dilemma” pattern, which helps you understand which element is important, or how to modify elements via Meta AI. Regarding the 2D Emotion Map, they will present how the Meta AI estimates players’ emotions and which parameters to change to make more compelling game situations.
Audiences will learn a general Meta AI design and a new 2D-Emotion-Map based approach. They will be able to conceptualize and implement Meta AI at production quality with various emotions such as “bored,” “relaxed,” or “excited” by modifying NPCs’ behaviors though means other than enemy spawning with a 2D Emotion Map.
Anyone who is curious or works in the field of artificial intelligence or game design. No advanced programming or AI experience is required to understand the lecture.