Keynotes

Valerie J. Shute

Professor Emerita in the Department of Educational Psychology and Learning Systems Florida State University

Stealth Assessment in Games to Measure and Support Learning

Well-designed games can be powerful vehicles to support learning, but this hinges on getting the assessment part right. Over the past decade, we have designed, developed, and evaluated a number of stealth assessments in games to see: (a) if they provide real-time, reliable, and valid estimates of students' developing competencies (e.g., physics understanding, creativity); (b) if students actually learn anything as a function of gameplay; (c) the added value of inserting engaging learning supports (cognitive and affective) into the mix; and (d) if the games are still fun and engaging with the embedded assessments and supports. My presentation will cover the topic of stealth assessment in games to measure and support important 21st century competencies, and touch on how this work can increase diversity in the STEM-related workforce. I'll focus on why it's important, what it is, and how to develop/accomplish it. I'll also provide examples and videos in the context of a game we developed called Physics Playground.

Valerie Shute is a Professor Emerita in the Department of Educational Psychology and Learning Systems at Florida State University. For more than four decades, she’s been involved with basic and applied research related to measurement, assessment, cognitive diagnosis, individual differences, and learning from advanced instructional systems. Her general research foci hover around the design, development, and evaluation of systems to enhance learning--particularly related to 21st century competencies. Over the past decade, her work has mainly focused on creating and using games with stealth assessment to support learning—of cognitive and noncognitive knowledge, skills, and dispositions (e.g., physics, problem solving, computational thinking, systems thinking, persistence, etc.). Her research has resulted in numerous grants, journal articles, books, chapters in books, as well as a patent (U.S. Patent #7,828,552: Method and System for Designing Adaptive, Diagnostic Assessments), and she has accrued over 25,000 citations according to Google Scholar. For more details on her research and publications see http://myweb.fsu.edu/vshute/

Julian Togelius

Associate Professor of Computer Science New York University

A roadmap to the AI revolution in (serious) games

Artificial intelligence is on everyone’s lips, and for game developers and researchers it is clear that there are plenty of opportunities for AI technologies to improve games and how we make them. But which kind of AI methods in particular? And where would they fit into your game? After all, AI research has been intertwined with games since its inception in the 1950s, although these days people tend to think about chatbots when prompted with the word AI. I will take you on a whirlwind tour of actual, near-future and far-future applications of AI in games and game development. The tour will cover game-playing, level generation, player modeling, NPCs, AI-based game engines and more.

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.