- This event has passed.
Michael Mateas – Gemini: An Interlinked Model of Game Generation & Interpretation
May 20, 2019 @ 3:00 pm - 4:30 pm
The Center for Computer Games Research invites you to a talk by Michael Mateas on Monday, the 20th of May.
Michael Mateas Michael Mateas is a Professor of Computational Media at University of California, Santa Cruz, where he helped launch the Computer Game Design degree, the first of its kind in the UC system. His work explores artificial intelligence-based art and entertainment, forging a new research discipline called Expressive AI. Michael Founded the Center for Games and Playable Media at UC Santa Cruz. Research interests include automated support for game generation, automatic generation of autonomous character conversations, story management, and authoring tools for interactive storytelling. With Andrew Stern, he created Façade, an award-winning interactive drama that uses AI techniques to combine rich autonomous characters with interactive plot control, creating the world’s first, fully-produced, real-time, interactive story. Façade is available for free download at http://www.interactivestory.net/. Michael received his BS in Engineering Physics from the University of the Pacific (1989), his MS in Computer Science from Portland State University (1993), and his Ph.D. in Computer Science (2002) from Carnegie Mellon University.
In this talk, Michael will discuss Gemini: An Interlinked Model of Game Generation and Interpretation. More about Gemini below:
Current approaches to game generation don’t understand the games they generate. As a result, even the most sophisticated systems in this regard, e.g., Game-o-Matic, betray this problem — generating games with goals that are at odds with their mechanics. We describe Gemini, the first bidirectional game generation and analysis system. Gemini is able to take games as input, perform a proceduralist reading of them, and produce possible interpretations that the games might afford. It can also take a desired interpretation as input and generate games consistent with the desired reading. For Gemini, we developed a game specification language capable of expressing a larger domain of games than is possible with VGDL, the most widespread formal game representation.