Julian Togelius

New York University
 http://julian.togelius.com/

Julian Togelius is an Associate Professor in the Department of Computer Science and Engineering, New York University, USA, and a co-founder and research director at mod.ai, Copenhagen. 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. He is 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.

Selected Publications:

  • Liu, Jialin, Sam Snodgrass, Ahmed Khalifa, Sebastian Risi, Georgios N. Yannakakis, and Julian Togelius. “Deep learning for procedural content generation.” Neural Computing and Applications (2020): 1-19.
  • Risi, Sebastian, and Julian Togelius. “Increasing generality in machine learning through procedural content generation.” Nature Machine Intelligence (2020): 1-9.
  • Togelius, Julian. Playing smart: On Games, Intelligence, and Artificial Intelligence. MIT Press, 2019.
  • Summerville, Adam, Sam Snodgrass, Matthew Guzdial, Christoffer Holmgård, Amy K. Hoover, Aaron Isaksen, Andy Nealen, and Julian Togelius. “Procedural content generation via machine learning (PCGML).” IEEE Transactions on Games 10, no. 3 (2018): 257-270.
  • Yannakakis, Georgios N., and Julian Togelius. Artificial Intelligence and Games. Springer, 2018.
  • Shaker, Noor, Julian Togelius, and Mark J. Nelson. Procedural Content Generation in Games. Springer, 2016.

    • Social Profiles

    All Sessions by Julian Togelius

    • 3. Keynote Afternoon

      Nov. 19

    • 16:00  - 16:45
      We want our games to be fun, or at least engaging. Designing an interactive experience so that it engages the user is at the core of the art of game design. But can we define what fun and engagement is? Can we measure it? And could we even create artificial intelligence that designs fun and engaging games? If we managed to do this, it would not only give us an incredibly useful tool, it would also teach us much about design and ourselves. I will discuss some ideas about fun and engagement, in particular those related to learning, curiosity, and game depth. I will then show some prototype systems that attempt to create fun or engaging game experiences and discuss about how we could move closer to the goal of automating fun.
      Where
      Online via Eventbrite




    Share

    Julian Togelius