It’s a long way from the IT University of Copenhagen to the NYU Tandon School of Engineering, but Julian Togelius is undaunted by the move. “New York is becoming the center of the indie game development community,” he says, “and I’m excited to have the chance to work with NYU faculty members like Katherine Isbister, Andy Nealen and Frank Lantz. I think some great collaborative gaming projects are in store.”
Togelius, a new member of the Department of Computer Science and Engineering, is at the forefront of the study of procedural content generation (PCG)—the process of creating game content (such as levels, maps, rules, and environments) by employing algorithms, rather than direct user input. Specifically, he has pioneered the use of evolutionary algorithms for such tasks. (Evolutionary algorithms are inspired by biological functions like reproduction, mutation, and natural selection.) These algorithms can work in tandem with other algorithms that recognize the player's skill and preferences to change the game on the fly. “We try to determine what you, as a gamer, are good at and what you enjoy doing within the game,” he explains. “When the game adapts to you as an individual player, it’s going to be more fun.”
In addition to creating customized games, PCG has the potential to make game development less costly (by eliminating the need for human designers) and more creative (because with intelligent design tools, even small teams or hobbyists could realize their visions without hundreds of hours of drudge work).
He and a group of colleagues in Denmark recently developed an artificial intelligence system that generates new card games from scratch, taking into account the number of players and their skill levels, winning conditions, and actions that can be completed each round. That type of system, he says, could have applications well beyond gaming and may one day have the potential to optimize turn-based processes like traffic lights.
With computing becoming pervasive, Togelius sees potential for such collaboration everywhere—in the past, he has collaborated with ubiquitous-computing researchers on recommender systems for surgeons in operating rooms—and that carries over to a large, diverse university like NYU. “I’ve lived and worked in Sweden, Denmark, Switzerland, and the United Kingdom,” he says. “I’m really excited to add New York City to that list.”