🔗 sites.google.com/ualberta.ca/...
@artificial-agency.bsky.social ) behaviour engine, presented by Chris Entwistle.
A box lunch will be provided for this last-day lunch keynote 🍱
@artificial-agency.bsky.social ) behaviour engine, presented by Chris Entwistle.
A box lunch will be provided for this last-day lunch keynote 🍱
Welcome Event separate registration: aaaiforms.wufoo.com/forms/aiide2...
Poster/Demo Session separate registration: aaaiforms.wufoo.com/forms/aiide2...
Welcome Event separate registration: aaaiforms.wufoo.com/forms/aiide2...
Poster/Demo Session separate registration: aaaiforms.wufoo.com/forms/aiide2...
Generalized Entropy and Solution Information for Measuring Puzzle Difficulty by Shen and Sturtevant
Puzzle entropy uses information entropy with respect to player knowledge to measure the difficulty of a puzzle. The paper generalizes and refines this idea.
Generalized Entropy and Solution Information for Measuring Puzzle Difficulty by Shen and Sturtevant
Puzzle entropy uses information entropy with respect to player knowledge to measure the difficulty of a puzzle. The paper generalizes and refines this idea.
🔗https://sites.google.com/ualberta.ca/aiide2025/registration
🔗https://sites.google.com/ualberta.ca/aiide2025/registration
There and Back Again: Extracting Formal Domains for Controllable Neurosymbolic Story Authoring by Kelly et al.
Language models create fluent narratives, while planning-based story generators offer control. This paper explores how to combine the best of both!
There and Back Again: Extracting Formal Domains for Controllable Neurosymbolic Story Authoring by Kelly et al.
Language models create fluent narratives, while planning-based story generators offer control. This paper explores how to combine the best of both!
Puck: A Slow and Personal Automated Game Designer by Michael Cook
The author outlines new goals for automated game design focused on users and communities. The result is Puck, an automated game design system with an exhaustive approach to content generation.
Puck: A Slow and Personal Automated Game Designer by Michael Cook
The author outlines new goals for automated game design focused on users and communities. The result is Puck, an automated game design system with an exhaustive approach to content generation.
⏰ Submission deadline: October 19th
🔍 More details: www.cs.mun.ca/~dchurchill/...
⏰ Submission deadline: October 19th
🔍 More details: www.cs.mun.ca/~dchurchill/...
MappyLand: Fast, Accurate Mapping for Console Games by Osborn et al.
Game maps are useful for humans, game-playing agents, and content generation. Mappyland uses a variety of heuristics and algorithms to automatically generate accurate maps from example play.
MappyLand: Fast, Accurate Mapping for Console Games by Osborn et al.
Game maps are useful for humans, game-playing agents, and content generation. Mappyland uses a variety of heuristics and algorithms to automatically generate accurate maps from example play.
sites.google.com/ualberta.ca/...
sites.google.com/ualberta.ca/...
“It’s Unwieldy and It Takes a Lot of Time” —Challenges and Opportunities for Creating Agents in Commercial Games by Jacob et al.
Game research should consider industry best practices; this paper interviews creators to identify challenges in making AI agents.
“It’s Unwieldy and It Takes a Lot of Time” —Challenges and Opportunities for Creating Agents in Commercial Games by Jacob et al.
Game research should consider industry best practices; this paper interviews creators to identify challenges in making AI agents.
sites.google.com/ualberta.ca/...
⏰ Early registration ends Oct 10, Don’t miss out!
sites.google.com/ualberta.ca/...
⏰ Early registration ends Oct 10, Don’t miss out!
Macro Action Selection with Deep Reinforcement Learning in StarCraft by Xu et al.
To reduce the gap between human players and StarCraft bots, Xu et al. propose using a Deep Reinforcement Learning framework to select macro actions instead of predefined rules.
Macro Action Selection with Deep Reinforcement Learning in StarCraft by Xu et al.
To reduce the gap between human players and StarCraft bots, Xu et al. propose using a Deep Reinforcement Learning framework to select macro actions instead of predefined rules.
sites.google.com/ualberta.ca/...
sites.google.com/ualberta.ca/...
CatSAT: A Practical, Embedded, SAT Language for Runtime PCG by Ian Douglas Horswill.
Runtime constraints can leave few resources available for constraint-based PCG in games. CatSAT is a solver designed with the reality of runtime resources in mind.
CatSAT: A Practical, Embedded, SAT Language for Runtime PCG by Ian Douglas Horswill.
Runtime constraints can leave few resources available for constraint-based PCG in games. CatSAT is a solver designed with the reality of runtime resources in mind.
Memory Bounded Monte Carlo Tree Search by Powley et al.
Information Set MCTS is a modification on MCTS for environments with imperfect information. In this paper, Powley et al. study memory bounding for this algorithm and implement it in a commercial game.
Memory Bounded Monte Carlo Tree Search by Powley et al.
Information Set MCTS is a modification on MCTS for environments with imperfect information. In this paper, Powley et al. study memory bounding for this algorithm and implement it in a commercial game.
📅 Proposals are now due Sep 19, 2025
🔍 More info here: sites.google.com/ualberta.ca/...
📅 Proposals are now due Sep 19, 2025
🔍 More info here: sites.google.com/ualberta.ca/...
Combining Gameplay Data with Monte CarloTree Search to Emulate Human Play by Devlin et al.
In collaboration with game developers, the authors improve MCTS by biasing decisions based on player data, making the agent more human-like without losing performance.
Combining Gameplay Data with Monte CarloTree Search to Emulate Human Play by Devlin et al.
In collaboration with game developers, the authors improve MCTS by biasing decisions based on player data, making the agent more human-like without losing performance.
Predicting Purchase Decisions in Mobile Free-to-Play Games by Sifa et al.
Understanding who is most likely to make purchases in a freemium mobile game is important for many reasons, and Sifa et al. proposed the first regression model to address this problem.
Predicting Purchase Decisions in Mobile Free-to-Play Games by Sifa et al.
Understanding who is most likely to make purchases in a freemium mobile game is important for many reasons, and Sifa et al. proposed the first regression model to address this problem.
Spice It Up! Enriching Open World NPC Simulation Using Constraint Satisfaction
By Černý et al.
Meaningful NPC interactions make games feel alive! This paper presents a constraint satisfaction method to apply pre-scripted interactions in open-world environments.
Spice It Up! Enriching Open World NPC Simulation Using Constraint Satisfaction
By Černý et al.
Meaningful NPC interactions make games feel alive! This paper presents a constraint satisfaction method to apply pre-scripted interactions in open-world environments.
The Combinatorial Multi-Armed Bandit Problem and its Application to Real-Time Strategy Games by Santiago Ontañón
The branching factor of some games makes MCTS unsuitable - until you try some of these alternative sampling strategies!
The Combinatorial Multi-Armed Bandit Problem and its Application to Real-Time Strategy Games by Santiago Ontañón
The branching factor of some games makes MCTS unsuitable - until you try some of these alternative sampling strategies!