These are the confirmed keynote speakers along with an abstract of their plenary talks.
|Jeff Orkin is a game developer, AI researcher, and PhD candidate in Professor Deb Roy's Cognitive Machines Group at the MIT Media Lab. His research focuses on Collective Artificial Intelligence -- data-driven content creation and planning for social interaction and dialogue in games, simulations, and virtual worlds. Prior to enrolling at the Media Lab, he developed several generations of AI systems in the game industry. As a Senior Engineer at Monolith Productions, he focused on goal-oriented autonomous character behavior and planning, while developing AI systems for No One Lives Forever 2 (NOLF2) and F.E.A.R. games.|
KEYNOTE: "Data-Driven Digital Actors" -> See the Slides <-
Characters in games have come a long way in the past 20 years, but it would be a stretch to call them actors. Actors have minds of their own. They can improvise and adapt to perform together with the rest of the cast. This talk will describe a new data-driven approach to authoring massive amounts of dialogue and behavior, and demonstrate how this approach supports open-ended, unscripted interaction with digital actors who can converse and work together with human players, via typed text or speech.
|Gillian Smith received her PhD in Computer Science from UC Santa Cruz, where she studied in the Center for Games and Playable Media. Her dissertation was titled "Expressive Design Tools: Procedural Content Generation for Game Designers". Recently she has started as an Assistant Professor at Northeastern University in Computer Science and Creative Industries. Her research interests are in how human designers can interact with procedural systems to create content for games, how to evaluate procedural content generators, and how procedural content generation can enable new playable experiences. Her other interests include gender and technology issues, especially women in games, and the use of games in education.|
KEYNOTE: "Expressive Design Tools" -> See the Slides <-
Game design requires an interdisciplinary team, with engineers, artists, designers, musicians, marketers, and many others working together. At the core of this process for digital games sits technology: games are shaped by the tools we use to make them and our ability to model the concepts they address. As AI researchers, we are always coming up with new technologies in the service of existing games; this talk encourages questioning how these technologies could be used to make new kinds of games or new kinds of design experiences. What is the game design purpose for our work? What new experiences are we enabling? How could game designers work with the technology we create? Specifically, this talk calls for the creation of what I call "expressive design tools": systems imbued with an understanding of a game's design that are sufficiently controllable and expressive for use in the design process. I describe my experience creating such a tool and how it enabled the creation of a completely new kind of game, and close with a discussion of open research problems in procedural content generation and expressive design tools.
|Michael Bowling is an associate professor at the University of Alberta. His research focuses on machine learning, games, and robotics, and he is particularly fascinated by the problem of how computers can learn to play games through experience. He is the leader of the Computer Poker Research Group, which has built some of the best poker playing programs on the planet. The programs have won international AI competitions as well as being the first to beat top professional players in a meaningful competition. He is also a principal investigator in the Reinforcement Learning and Artificial Intelligence (RLAI) group and the Alberta Ingenuity Centre for Machine Learning (AICML).|
KEYNOTE: "Abstraction with an Adversary" -> See the Slides <-
The Computer Poker Research Group at the University of Alberta has for well over a decade developed the strongest poker playing programs in the world. We have tested them in competition against other programs, winning 20 of 33 events since the inauguration of the AAAI Computer Poker Competition in 2006. We have also tested them against top professional players, becoming the first to beat professional poker players in a meaningful competition in 2008. This success all originates from our key approach: when facing an intractably large game, abstract the game to a smaller one and reason in that game. Recently, this approach has been shown to be on shaky ground, or rather on no ground at all. In this talk, I'll be looking down to see what, if anything, the poker success is standing on; and what this line of research means for real-world applications which don't involve an apparent adversary.
Short Talk: "General Atari 2600 Game Player" -> See the Slides <-
Version 2.5 - September, 2012