AI-driven Experience Management for Fun and Training
Virtual worlds have been extensively used for training and entertainment. A player’s experience in such worlds can be managed by an external agent towards achieving certain pedagogical or recreational objectives. To facilitate a mass-scale deployment and/or to achieve consistent results, the external manager can be coded algorithmically. In this talk we will present development and evaluation of several such Artificial Intelligence experience managers. We will focus on interactive storytelling where the player has the agency to change the narrative he/she is experiencing in a virtual world. Specifically, we will present several computational models for explicitly modeling a player and using the model to manage the virtual world. As case studies, we will consider several implementations using commercial video-game engines.
Vadim Bulitko is an Associate Professor at the University of Alberta (Department of Computing Science). He received his Ph.D. in computer science from the University of Illinois at Urbana-Champaign in 1999. Vadim is interested in building the strong artificial intelligence as well as understanding intelligence and cognition in humans and animals. He specializes in real-time heuristic search, AI in computer games including interactive narrative and cognitive processes and models.