Tue, Feb 15, 2022 @ 04:00 PM - 05:20 PM
Conferences, Lectures, & Seminars
Speaker: Julian Togelius, New York University
Talk Title: Generating content for fun, games, and intelligence
Series: Computer Science Colloquium
Abstract: Designing and developing video games is hard work. Much of that work goes into designing the environments, levels, characters, items, and graphical assets that the player interacts with. For decades, some games have featured procedural content generation, where parts of the game was generated algorithmically as it was being played. Recently, we have seen an explosion of interest in this field, with many new techniques being applied to content generation problems. As video games are increasingly shaping culture and society, including visions of the so called "metaverse", these problems and their solutions are becoming increasingly important. But could procedural content generation also play a role outside of what we think of as games, in fields such as architecture, interior design, and robotics? And can we further the development of artificial general intelligence by generating new tasks and environments to optimally challenge our developing artificial intelligences? I will lay out some visions for this and show some recent approaches to generating game content, based on methods as diverse as evolutionary computation, reinforcement learning, self-supervised learning, and constraint solving.
***Prof. Julian Togelius will give his talk in person at SGM 124 and we will also host the talk over Zoom.***
Register in advance for this webinar at:
After registering, attendees will receive a confirmation email containing information about joining the webinar.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Julian Togelius is an Associate Professor in the Department of Computer Science and Engineering, New York University, and a co-founder of modl.ai. He works on artificial intelligence for games and on games for artificial intelligence. His current main research directions involve procedural content generation in games, general video game playing, player modeling, and fair and relevant benchmarking of AI through game-based competitions. Additionally, he works on topics in evolutionary computation, quality-diversity algorithms, and reinforcement learning. From 2018 to 2021, he was the Editor-in-Chief of the IEEE Transactions on Games. Togelius holds a BA from Lund University, an MSc from the University of Sussex, and a PhD from the University of Essex. He has previously worked at IDSIA in Lugano and at the IT University of Copenhagen.
Host: Stefanos Nikolaidis
Location: Seeley G. Mudd Building (SGM) - 124
Audiences: Everyone Is Invited
Contact: Computer Science Department