Matthew Guzdial
@matthewguz.bsky.social
Associate professor @ University of Alberta and Canada CIFAR AI Chair @ Alberta Machine Intelligence Institute.
Games, machine learning, and creativity | he/him
Games, machine learning, and creativity | he/him
#AIIDE25 wrapped! Thanks to everyone who made this year’s @aiide.bsky.social such a success. We’ll be back soon with announcements for ’26’s location and call, plus the ‘25 recordings. But for now I’m going to turn off my brain for 48 hours.
November 15, 2025 at 12:40 AM
#AIIDE25 wrapped! Thanks to everyone who made this year’s @aiide.bsky.social such a success. We’ll be back soon with announcements for ’26’s location and call, plus the ‘25 recordings. But for now I’m going to turn off my brain for 48 hours.
Exciting to find out that I’m still going to be at EXAG in 10 years! And that I’ll have regressed to be 20 years younger by then!
November 11, 2025 at 6:26 PM
Exciting to find out that I’m still going to be at EXAG in 10 years! And that I’ll have regressed to be 20 years younger by then!
EXAG/INT Workshop Keynote from Mike Cook @mtrc.bsky.social with incredible slide design. Shout outs @bombsfall.bsky.social
November 11, 2025 at 4:41 PM
EXAG/INT Workshop Keynote from Mike Cook @mtrc.bsky.social with incredible slide design. Shout outs @bombsfall.bsky.social
Plus this initiative by Richard Zhao @richardzhao.bsky.social to track where all our roughly 120 attendees originate from!
November 10, 2025 at 4:30 PM
Plus this initiative by Richard Zhao @richardzhao.bsky.social to track where all our roughly 120 attendees originate from!
Swag this year includes AIIDE and EXAG stickers plus this incredible pin design from Dagmar Lofts @dagmarlofts.bsky.social!
November 10, 2025 at 4:24 PM
Swag this year includes AIIDE and EXAG stickers plus this incredible pin design from Dagmar Lofts @dagmarlofts.bsky.social!
So sorry to hear that! Here’s Goo and Vincent our geriatric angels
September 6, 2025 at 2:36 AM
So sorry to hear that! Here’s Goo and Vincent our geriatric angels
Excited to announce that our work on Reinforcement Learning for Arachnophobia treatment has been accepted at ACM Transactions on Interactive Intelligent Systems! We found that an RL agent could more effectively adapt VR spiders to achieve specified anxiety levels in users compared to current SOTA.
August 25, 2025 at 1:39 AM
Excited to announce that our work on Reinforcement Learning for Arachnophobia treatment has been accepted at ACM Transactions on Interactive Intelligent Systems! We found that an RL agent could more effectively adapt VR spiders to achieve specified anxiety levels in users compared to current SOTA.
Dagstuhl is going well
July 16, 2025 at 12:22 PM
Dagstuhl is going well
When else am I gonna get a chance to do one of these?
(I'm tenured)
(I'm tenured)
July 8, 2025 at 8:24 PM
When else am I gonna get a chance to do one of these?
(I'm tenured)
(I'm tenured)
You can make some pretty fun things with it! Thanks to TWOSE for having me as their Science Fellow for 2025!
Github link: github.com/mguzdial3/Cu...
Github link: github.com/mguzdial3/Cu...
July 1, 2025 at 10:58 PM
You can make some pretty fun things with it! Thanks to TWOSE for having me as their Science Fellow for 2025!
Github link: github.com/mguzdial3/Cu...
Github link: github.com/mguzdial3/Cu...
PEAK has the juice
June 25, 2025 at 2:42 AM
PEAK has the juice
Saturday I ran the second edition of the Upper Bound-associated AI and Games workshop with special guests Dr. Seth Cooper, @amidos2006.bsky.social, and @maxkreminski.bsky.social! Great conversations on modelling player knowledge, designer intent, and tension curves as a language for game design.
May 26, 2025 at 3:13 PM
Saturday I ran the second edition of the Upper Bound-associated AI and Games workshop with special guests Dr. Seth Cooper, @amidos2006.bsky.social, and @maxkreminski.bsky.social! Great conversations on modelling player knowledge, designer intent, and tension curves as a language for game design.
For example, I could visualize how the possible outcomes shifted before (left) and after (right) a seemingly small rules change. Each dot in these images is a single simulated game of 1000 simulated games. The size of the dots showed how many times that outcome happened. Watch out soldiers!
May 13, 2025 at 3:51 PM
For example, I could visualize how the possible outcomes shifted before (left) and after (right) a seemingly small rules change. Each dot in these images is a single simulated game of 1000 simulated games. The size of the dots showed how many times that outcome happened. Watch out soldiers!
Ran a 22 person murder mystery dinner themed as a spoof on AI startups for my lab tonight as an end of term celebration. “Gatthew Muzdial’s” death was avenged thanks to the security guards he hired to keep him alive.
April 17, 2025 at 2:39 AM
Ran a 22 person murder mystery dinner themed as a spoof on AI startups for my lab tonight as an end of term celebration. “Gatthew Muzdial’s” death was avenged thanks to the security guards he hired to keep him alive.
March 26, 2025 at 9:21 PM
And of course if I can be selfish our work on "Morai Maker", a level design tool built in collaboration with game developers and evaluated by published game developers. Published in "Friend, collaborator, student, manager: How design of an ai-driven game level editor affects creators"
March 24, 2025 at 11:08 PM
And of course if I can be selfish our work on "Morai Maker", a level design tool built in collaboration with game developers and evaluated by published game developers. Published in "Friend, collaborator, student, manager: How design of an ai-driven game level editor affects creators"
Dr. Cor-Paul Bezemer meanwhile has been directly collaborating with the games industry for automated bug detection and accessibility work, here an example example from "Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models"
March 24, 2025 at 11:08 PM
Dr. Cor-Paul Bezemer meanwhile has been directly collaborating with the games industry for automated bug detection and accessibility work, here an example example from "Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models"
And of course there's great examples of using interviews to gain knowledge directly from game devs. Kristen K. Yu (now Zynga) did this with "The Definition-Context-Purpose Paradigm..." for quests and Worrall and Collins for music in "Considerations and Concerns of Professional Game Composers..."
March 24, 2025 at 11:08 PM
And of course there's great examples of using interviews to gain knowledge directly from game devs. Kristen K. Yu (now Zynga) did this with "The Definition-Context-Purpose Paradigm..." for quests and Worrall and Collins for music in "Considerations and Concerns of Professional Game Composers..."
On the academia->industry side a real champion has been Dr. Nathan Sturtevant. On the left a figure from Sturtevant's "A sparse grid representation for dynamic three-dimensional worlds" (2011!) Dragon Age work and the right "Pathfinding and Abstraction with Dynamic Terrain Costs" for Nightingale.
March 24, 2025 at 11:08 PM
On the academia->industry side a real champion has been Dr. Nathan Sturtevant. On the left a figure from Sturtevant's "A sparse grid representation for dynamic three-dimensional worlds" (2011!) Dragon Age work and the right "Pathfinding and Abstraction with Dynamic Terrain Costs" for Nightingale.