*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
~Title: Automated Iterative Game Design
Alexander Zook
School of Interactive Computing
College of Computing
Georgia Institute of Technology
Date: Monday, October 17th, 2016
Time: 11am
Location: TSRB 223
Committee:
---------
Dr. Mark Riedl (Advisor, School of Interactive Computing, Georgia Tech)
Dr. Brian Magerko (Co-Advisor, School of Literature, Media, Communication, Georgia Tech)
Dr. Charles Isbell (School of Interactive Computing, Georgia Tech)
Dr. Ashok Goel (School of Interactive Computing, Georgia Tech)
Dr. Michael Mateas (Computational Media Department, University of California, Santa Cruz)
Dr. Jeff Orkin (Giant Otter Technologies)
Abstract:
--------
Artificial intelligence research has long sought to enable machines to be creative as a way to better understand human creativity, understand the limitations of computation as a means for machines to be creative, and to potentially augment human creative practices. Games have emerged as a unique domain of creative practice where the artifacts produced are interactive. Game design and development are also being recognized as valuable human skills with a growing body of amateur creators.
Game generation research has applied artificial intelligence to augment and understand human game creation. To date, these systems have been limited to specific game genres and have not learned how their games influence their audiences. Limiting a system to specific genres constrains the use of that system and hampers insights into general game design skills that apply across genres. Further, any system that does not learn from its audience cannot ensure the games it makes work for its audience.
In this thesis I developed systems to model an iterative game design process that underpins many common creative practices. The systems developed capture general methods for generating games across a variety of domains, simulating play in those games, evaluating the space of play available in those games, and efficiently iterating on the design of those games. By developing systems capable of general game design iteration this thesis lays the groundwork for studying shared aspects of iterative design practices across game genres as a model of a general creative process.
