Embedded Files
Dr. Gita Sukthankar
Dr. Gita Sukthankar
Professor, University of Central Florida
Teams in Games
Teams in Games
Andrew Carnegie had a famous quote about teamwork: “Teamwork is the ability to work together toward a common vision. The ability to direct individual accomplishments toward organizational objectives. It is the fuel that allows common people to attain uncommon results." However, the reality is that teams, particularly virtual ones, can be frustrating, and many teams consistently fail to reach their objectives. This talk presents an overview of my research on Minecraft player teams conducted as part of DARPA’s ASIST (AI for Successful Teams) program. We introduce a new sequential pattern mining technique for extracting patterns that distinguish good teams from bad ones and also examine the use of natural language processing to detect conflict in teams in a generalizable way. Finally, I’ll present my new work on developing a testbed for studying teamwork in tabletop role playing games such as Dungeons and Dragons.
Bio: Dr. Gita Sukthankar is a Professor in the Computer Science Department at University of Central Florida. She served as program chair and general chair of the AIIDE conference in 2012 and 2013. Dr. Sukthankar received her Ph.D. from the Robotics Institute at Carnegie Mellon and an A.B. in psychology from Princeton University. She is a recipient of AFOSR Young Investigator, DARPA CSSG, and NSF CAREER awards, as well as numerous UCF awards for research excellence. Dr. Sukthankar has served on the boards of the International Foundation for Autonomous Agents and Multi-agent Systems (IFAAMAS) and DARPA's Information Science and Technology (ISAT) advisory group. She has edited two books (Plan, Activity, and Intent Recognition and Social Interactions in Virtual Worlds).
Dr. Robert Zubek
Dr. Robert Zubek
Architect, Applied AI, Zynga
Future Perfect: AI in games, looking back, looking ahead
Future Perfect: AI in games, looking back, looking ahead
AI in games has grown like a katamari ball, starting from modest, NPC-oriented beginnings, but quickly rolling up a vast array of complex topics across the wider game development domain. From simulating individual characters to vast worlds, from modeling physical actions to conversations to visual presentation, from runtime control to design-time co-creation, game AI is making inroads everywhere - and often with great success. Following the theme of “20/20 Vision”, in this talk we will look back at the growth of this field from the industry perspective, and the growth of collaboration between academia and industry - and see how this past trajectory can inform our work in the future.
Bio: Dr. Robert Zubek is a veteran game developer and engineering architect in Applied AI at Zynga. He works in artificial intelligence, game design, and game systems engineering, with responsibilities ranging from AI systems to entire commercial games. He is also active in design practice and education, and his textbook “Elements of Game Design” is available from MIT Press. Beyond his work at Zynga, Dr. Zubek worked at Electronic Arts and Three Rings / Sega, and co-founded SomaSim and the Chicago Game Lab. He holds a Ph.D. from Northwestern University and has been a member of the AIIDE community since the inaugural conference, which he feels was only a short time ago no matter what the calendar says.
Dr. Mark Riedl
Dr. Mark Riedl
Professor, Georgia Institute of Technology
Dungeons and DQNs: The Serious Quest for Open-Ended Role Playing Game Agents
Dungeons and DQNs: The Serious Quest for Open-Ended Role Playing Game Agents
As artificial intelligence increases in capacity, we might one day hope to introduce agents into open-ended environments. In those environments, we might expect our agents to interact with, and be directed by, humans teammates. What can we learn from teaching AI agents to play computer games? For conventional digital computer games, sampling simulated environments can often achieve human level game play performance in closed-world games. However, language-based role-playing games are open-ended with respect to near infinite possibilities. They require agents to both understand the world the way humans do but also perform behavior that is understandable to humans. In this talk, I present the case for studying human-AI interaction through role-playing games, using nearly two decades of research on interactive storytelling and role-playing to illustrate the challenges and opportunities.
Bio: Dr. Mark Riedl is a Professor in the Georgia Tech School of Interactive Computing and Associate Director of the Georgia Tech Machine Learning Center. Dr. Riedl’s research focuses on human-centered artificial intelligence—the development of artificial intelligence and machine learning technologies that understand and interact with human users in more natural ways. Dr. Riedl’s recent work has focused on story understanding and generation, computational creativity, explainable AI, and teaching virtual agents to behave safely.
Page updated
Report abuse