Matthew Guzdial

Matthew Guzdial
University of Alberta | UAlberta · Department of Computing Science

Doctor of Philosophy

About

111
Publications
13,854
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
938
Citations
Introduction
Matthew Guzdial is an Assistant Professor at the University of Alberta. His work focuses on the intersection of artificial intelligence (specifically machine learning), computational creativity, and human-computer interaction.

Publications

Publications (111)
Article
Game development is a highly technical practice that traditionally requires programming skills. This serves as a barrier to entry for would-be developers or those hoping to use games as part of their creative expression. While there have been prior game development tools focused on accessibility, they generally still require programming, or have ma...
Article
Modern commercial games are designed for mass appeal, not for individual players, but there is a unique opportunity in video games to better fit the individual through adapting elements in games. In this paper, we focus on AI Directors, systems which can dynamically modify a game, that attempt to personalize the player experience to a player's pref...
Article
Open datasets are the foundation of many types of academic research. One field that requires datasets is data-driven player modeling, but there is a lack of variety in existing datasets. We introduce the FarmQuest Player Telemetry (FPT) dataset, a new playthrough dataset of a cozy farming game. We envision this dataset will be used for reproducing...
Article
Player Experience Modelling (PEM) is the study of AI techniques applied to modelling a player's experience within a video game. PEM development can be labour-intensive, requiring expert hand-authoring or specialized data collection. In this work, we propose a novel PEM development approach, approximating player experience from gameplay video. We ev...
Preprint
Full-text available
Player Experience Modelling (PEM) is the study of AI techniques applied to modelling a player's experience within a video game. PEM development can be labour-intensive, requiring expert hand-authoring or specialized data collection. In this work, we propose a novel PEM development approach, approximating player experience from gameplay video. We ev...
Preprint
Full-text available
Modern commercial games are designed for mass appeal, not for individual players, but there is a unique opportunity in video games to better fit the individual through adapting game elements. In this paper, we focus on AI Directors, systems which can dynamically modify a game, that personalize the player experience to match the player's preference....
Preprint
Full-text available
Personalized virtual reality exposure therapy is a therapeutic practice that can adapt to an individual patient, leading to better health outcomes. Measuring a patient's mental state to adjust the therapy is a critical but difficult task. Most published studies use subjective methods to estimate a patient's mental state, which can be inaccurate. Th...
Preprint
Full-text available
The need to generate a spider to provoke a desired anxiety response arises in the context of personalized virtual reality exposure therapy (VRET), a treatment approach for arachnophobia. This treatment involves patients observing virtual spiders in order to become desensitized and decrease their phobia, which requires that the spiders elicit specif...
Article
Procedural Content Generation (PCG) is the algorithmic generation of content, often applied to games. PCG and PCG via Machine Learning (PCGML) have appeared in published games. However, it can prove difficult to apply these approaches in the early stages of an in-development game. PCG requires expertise in representing designer notions of quality i...
Article
Procedural Content Generation (PCG) and Procedural Content Generation via Machine Learning (PCGML) have been used in prior work for generating levels in various games. This paper introduces Content Augmentation and focuses on the subproblem of level inpainting, which involves reconstructing and extending video game levels. Drawing inspiration from...
Article
Automated game design (AGD), the study of automatically generating game rules, has a long history in technical games research. AGD approaches generally rely on approximations of human play, either objective functions or AI agents. Despite this, the majority of these approximators are static, meaning they do not reflect human player's ability to lea...
Preprint
Procedural Content Generation via Machine Learning (PCGML) faces a significant hurdle that sets it apart from other fields, such as image or text generation, which is limited annotated data. Many existing methods for procedural level generation via machine learning require a secondary representation besides level images. However, the current method...
Preprint
Game level blending via machine learning, the process of combining features of game levels to create unique and novel game levels using Procedural Content Generation via Machine Learning (PCGML) techniques, has gained increasing popularity in recent years. However, many existing techniques rely on human-annotated level representations, which limits...
Preprint
We introduce the concept of Procedural Content Generation via Knowledge Transformation (PCG-KT), a new lens and framework for characterizing PCG methods and approaches in which content generation is enabled by the process of knowledge transformation -- transforming knowledge derived from one domain in order to apply it in another. Our work is motiv...
Article
We introduce the concept of Procedural Content Generation via Knowledge Transformation (PCG-KT), a new lens and framework for characterizing PCG methods and approaches in which content generation is enabled by the process of knowledge transformation—transforming knowledge derived from one domain in order to apply it in another. Our work is motivate...
Chapter
We began this book by pointing out that the history of PCGML only began in 2013, and stating that we’d cover open problems in PCGML in this chapter. But as a matter of fact all of PCGML is an open problem. But the field is changing constantly, so it’s unclear how long these problems will remain open. Here we will attempt to cover open problems. But...
Chapter
In the previous chapter we introduced our first category of PCGML techniques, namely, constraint-based PCGML. Constraint-based PCGML approaches rely on data to build a model representing the structures and relationships that are allowed and not allowed between a set of variables. But what if we want to instead capture how likely or common a relatio...
Chapter
In the previous chapter we used sequence-based Deep Neural Networks (both Recurrent and Transformer based), but sequences are only one possible way for us to represent the content that we wish to generate. For some types of content (like levels that have one dimension that is much larger than the others), this representation makes sense as the cont...
Chapter
In this final chapter we cover a variety of resources in an effort to help readers get started with their own PCGML projects, and then end with some final conclusions and takeaways.
Chapter
So let’s say you want to use PCGML to generate something, which seems a reasonable assumption if you’re reading this book. In this chapter we’ll overview a high level process for doing just that, discussing practical and ethical considerations as we go. We break this process into four steps: (1) produce or acquire training data, (2) train the model...
Chapter
In the previous chapter, we discussed neural networks, building up from the smallest possible neural networks to ‘deep’ networks with many hidden layers. In this chapter, we introduce neural networks that are capable of handling sequential inputs of arbitrary lengths. We work through multiple forms of PCG that are suitable for a sequential represen...
Chapter
The other chapters in this book cover a wide range of approaches to procedural content generation that leverage different machine learning paradigms. Before jumping into the machine learning-based approaches, we will use this chapter to give a brief introduction to classical (i.e., non-machine learning-based) PCG approaches to provide context for t...
Chapter
In the previous chapters we introduced different machine learning paradigms and discussed how they could be leveraged for PCGML. What each of those previous chapters had in common was that they treated training and generation as static processes. That is, model training and content generation were processes that someone would start and then wait fo...
Chapter
In Chap. 3 we introduced linear regression, a linear model that learns a set of weights to apply to an input, in hopes of finding the model with the lowest error. However, linear models are limited in the behaviors that they can learn. In this chapter we learn about Neural Networks, a class of model that are capable of learning any possible functio...
Chapter
In the previous chapter, we discussed various forms of non-Machine Learning based Procedural Content Generation, but before we dive into Procedural Content Generation via Machine Learning (PCGML), we must first discuss what Machine Learning (ML) even is. At its core, ML is a set of techniques for learning functions—a process of finding a mapping fr...
Chapter
All the way back in Chap. 2 we discussed search-based PCG (SBPCG). This was an approach to generate game content by authoring a space of possible content, away to move through that space (metaphorically, literally it involves editing some current piece of content), and then some way of evaluating the content (a quantitative measure of content quali...
Chapter
In Sect. 2.2 we introduced constraint satisfaction approaches to PCG. Recall that constraint-based approaches use a set of variables, each with a range of possible values, and a set of constraints that must be satisfied over the variables and outputs. In Sect. 2.2 we walked through an example of how we could formulate the problem of generating pali...
Preprint
Player modelling is the field of study associated with understanding players. One pursuit in this field is affect prediction: the ability to predict how a game will make a player feel. We present novel improvements to affect prediction by using a deep convolutional neural network (CNN) to predict player experience trained on game event logs in tand...
Preprint
Real-Time Strategy (RTS) game unit generation is an unexplored area of Procedural Content Generation (PCG) research, which leaves the question of how to automatically generate interesting and balanced units unanswered. Creating unique and balanced units can be a difficult task when designing an RTS game, even for humans. Having an automated method...
Preprint
In fighting games, individual players of the same skill level often exhibit distinct strategies from one another through their gameplay. Despite this, the majority of AI agents for fighting games have only a single strategy for each "level" of difficulty. To make AI opponents more human-like, we'd ideally like to see multiple different strategies a...
Preprint
There has been significant research interest in Procedural Level Generation via Machine Learning (PLGML), applying ML techniques to automated level generation. One recent trend is in the direction of learning representations for level design via embeddings, such as tile embeddings. Tile Embeddings are continuous vector representations of game level...
Article
Reinforcement learning (RL) is a powerful way to solve sequential decision-making tasks. However training an RL agent in a complex environment requires a large amount of interactions, which is non-ideal when acting in an environment is costly or dangerous. One alternative is to learn an approximation of the real environment, referred to as a world...
Article
Players can sometimes engage with parts of a video game that they do not enjoy if the game does not try to adapt the experience to the player’s preference. AI directors have been used in the past to tailor player experience to different people. In industry, AI directors are relatively uncommon and are typically domain-specific and rules-based. In t...
Article
In AI director research, it is not straightforward for researchers to understand how each algorithm affects the player experience. This demo introduces PWR, which is a new fully developed video game test bed to evaluate AI directors. This demo includes 3 different AI director algorithms in order to help researchers improve their intuition for under...
Chapter
Each chapter should be preceded by an abstract (no more than 200 words) that summarizes the content. The abstract will appear online at www.SpringerLink.com and be available with unrestricted access. This allows unregistered users to read the abstract as a teaser for the complete chapter. Please use the ’starred’ version of the abstract command for...
Preprint
Explainable Artificial Intelligence (XAI) methods are intended to help human users better understand the decision making of an AI agent. However, many modern XAI approaches are unintuitive to end users, particularly those without prior AI or ML knowledge. In this paper, we present a novel XAI approach we call Responsibility that identifies the most...
Preprint
2D animation is a common factor in game development, used for characters, effects and background art. It involves work that takes both skill and time, but parts of which are repetitive and tedious. Automated animation approaches exist, but are designed without animators in mind. The focus is heavily on real-life video, which follows strict laws of...
Conference Paper
To best assist human designers with different styles, Machine Learning (ML) systems need to be able to adapt to them. However, there has been relatively little prior work on how and when to best adapt an ML system to a co-designer. In this paper we present threshold designer adaptation: a novel method for adapting a creative ML model to an individu...
Preprint
To best assist human designers with different styles, Machine Learning (ML) systems need to be able to adapt to them. However, there has been relatively little prior work on how and when to best adapt an ML system to a co-designer. In this paper we present threshold designer adaptation: a novel method for adapting a creative ML model to an individu...
Preprint
One major barrier to applications of deep Reinforcement Learning (RL) both inside and outside of games is the lack of explainability. In this paper, we describe a lightweight and effective method to derive explanations for deep RL agents, which we evaluate in the Atari domain. Our method relies on a transformation of the pixel-based input of the RL...
Preprint
In recent years, Procedural Level Generation via Machine Learning (PLGML) techniques have been applied to generate game levels with machine learning. These approaches rely on human-annotated representations of game levels. Creating annotated datasets for games requires domain knowledge and is time-consuming. Hence, though a large number of video ga...
Preprint
Personalized therapy, in which a therapeutic practice is adapted to an individual patient, leads to better health outcomes. Typically, this is accomplished by relying on a therapist's training and intuition along with feedback from a patient. While there exist approaches to automatically adapt therapeutic content to a patient, they rely on hand-aut...
Preprint
Mixed-initiative Procedural Content Generation (PCG) refers to tools or systems in which a human designer works with an algorithm to produce game content. This area of research remains relatively under-explored, with the majority of mixed-initiative PCG level design systems using a common set of search-based PCG algorithms. In this paper, we introd...
Preprint
Architecture search optimizes the structure of a neural network for some task instead of relying on manual authoring. However, it is slow, as each potential architecture is typically trained from scratch. In this paper we present an approach called Conceptual Expansion Neural Architecture Search (CENAS) that combines a sample-efficient, computation...
Article
Mixed-initiative Procedural Content Generation (PCG) refers to tools or systems in which a human designer works with an algorithm to produce game content. This area of research remains relatively under-explored, with the majority of mixed-initiative PCG level design systems using a common set of search-based PCG algorithms. In this paper, we introd...
Article
A character’s appearance is crucial to communicating game mechanics to the audience. Creating a game character’s design is a time-consuming task and requires design knowledge, skills, and experience. Research on how an AI system might be able to support this design process is an underexplored area. In this work we present a prototype of a variation...
Article
Chart creation for rhythm action games is a time consuming task that requires specialized design knowledge. While chart generation systems have been explored in the past, there are currently no co-creative chart authoring systems. In this paper, we present KiaiTime, a mixed-initiative, co-creative PCGML editor for the rhythm game Taiko no Tatsujin....
Article
One major barrier to applications of deep Reinforcement Learning (RL) both inside and outside of games is the lack of explainability. In this paper, we describe a lightweight and effective method to derive explanations for deep RL agents, which we evaluate in the Atari domain. Our method relies on a transformation of the pixel-based input of the RL...
Article
Full-text available
Personalized therapy, in which a therapeutic practice is adapted to an individual patient, leads to better health outcomes. Typically, this is accomplished by relying on a therapist's training and intuition along with feedback from a patient. While there exist approaches to automatically adapt therapeutic content to a patient, they rely on hand-aut...
Article
In recent years, Procedural Level Generation via Machine Learning (PLGML) techniques have been applied to generate game levels with machine learning. These approaches rely on human-annotated representations of game levels. Creating annotated datasets for games requires domain knowledge and is time-consuming. Hence, though a large number of video ga...
Article
Among academic communities there is no single agreed upon definition of a quest. The industry perspective on this topic is also largely unknown. Thus, the purpose of this paper is to gain an understanding of the definition of a quest from industry professionals to better inform the academic community. We interviewed fifteen game developers with exp...
Preprint
Generating rhythm game charts from songs via machine learning has been a problem of increasing interest in recent years. However, all existing systems struggle to replicate human-like patterning: the placement of game objects in relation to each other to form congruent patterns based on events in the song. Patterning is a key identifier of high qua...
Preprint
Full-text available
Procedural content generation via machine learning (PCGML) is the process of procedurally generating game content using models trained on existing game content. PCGML methods can struggle to capture the true variance present in underlying data with a single model. In this paper, we investigated the use of ensembles of Markov chains for procedurally...
Preprint
Co-creative Procedural Content Generation via Machine Learning (PCGML) refers to systems where a PCGML agent and a human work together to produce output content. One of the limitations of co-creative PCGML is that it requires co-creative training data for a PCGML agent to learn to interact with humans. However, acquiring this data is a difficult an...
Preprint
Machine learning has been a popular tool in many different fields, including procedural content generation. However, procedural content generation via machine learning (PCGML) approaches can struggle with controllability and coherence. In this paper, we attempt to address these problems by learning to generate human-like paths, and then generating...
Preprint
Autonomous game design, generating games algorithmically, has been a longtime goal within the technical games research field. However, existing autonomous game design systems have relied in large part on human-authoring for game design knowledge, such as fitness functions in search-based methods. In this paper, we describe an experiment to attempt...
Article
Automatic analysis of game levels can provide as- sistance to game designers and procedural content generation. We introduce a static-dynamic scale to categorize level analysis strategies, which captures the extent that the analysis depends on player simulation. Due to its ability to automatically learn intermediate representations for the task, a...
Article
The AIIDE Playable Experiences track celebrates innovations in how AI can be used in polished interactive experiences. Four 2016 accepted submissions display a diversity of approaches. Rogue Process combines techniques for medium-permanence procedurally generated hacking worlds. Elsinore applies temporal predicate logic to enable a time-traveling n...
Article
A touted use of Procedural Content Generation is generating content tailored to specific players. Previous work has relied on human identification of player profile features which are then mapped to level generator features. We present a machine-learned technique to train generators on Super Mario Bros. videos, generating levels based on latent pla...
Article
In this paper we describe a level design editor designed as an interface to allow different AI agents to creatively collaborate on level design problems with human designers. We intend to investigate the comparative impacts of different AI techniques on user experience in this context.
Article
Automated game design is the problem of automatically producing games through computational processes. Traditionally, these methods have relied on the authoring of search spaces by a designer, defining the space of all possible games for the system to author. In this paper, we instead learn representations of existing games from gameplay video and...
Preprint
Procedural content generation via machine learning (PCGML) has shown success at producing new video game content with machine learning. However, the majority of the work has focused on the production of static game content, including game levels and visual elements. There has been much less work on dynamic game content, such as game mechanics. One...
Preprint
Procedural Content Generation via Machine Learning (PCGML) refers to a group of methods for creating game content (e.g. platformer levels, game maps, etc.) using machine learning models. PCGML approaches rely on black box models, which can be difficult to understand and debug by human designers who do not have expert knowledge about machine learnin...
Preprint
In game development, designing compelling visual assets that convey gameplay-relevant features requires time and experience. Recent image generation methods that create high-quality content could reduce development costs, but these approaches do not consider game mechanics. We propose a Convolutional Variational Autoencoder (CVAE) system to modify...
Conference Paper
Procedural content generation via machine learning (PCGML) has recently gained research attention due to its ability to generate new game content with minimal user input. However, thus far those without machine learning expertise have been largely unable to use PCGML to generate content to fit their needs. This paper proposes the use of images as t...
Article
Mixed-initiative procedural content generation (PCG) refers to systems where a human and AI cooperate in some way to produce content. While there has been increasing interest in research on these systems, there are still many domains and PCG approaches that have not yet been explored. In this demonstration we introduce a novel mixed-initiative tool...
Article
Procedural content generation via machine learning (PCGML) has recently gained research attention due to its ability to generate new game content with minimal user input. However, thus far those without machine learning expertise have been largely unable to use PCGML to generate content to fit their needs. This paper proposes the use of images as t...
Article
Human designers may find it difficult to anticipate the impact of small changes to some games, particularly in puzzle games. However, it is not difficult for computers to simulate all mechanical impacts of such small changes. This suggests that computers might be able to aid humans designers as they build and analyze game levels. This paper takes o...
Preprint
Full-text available
Tabletop roleplaying games (TTRPGs) and procedural content generators can both be understood as systems of rules for producing content. In this paper, we argue that TTRPG design can usefully be viewed as procedural content generator design. We present several case studies linking key concepts from PCG research -- including possibility spaces, expre...
Preprint
Full-text available
Automated game design is the problem of automatically producing games through computational processes. Traditionally these methods have relied on the authoring of search spaces by a designer, defining the space of all possible games for the system to author. In this paper we instead learn representations of existing games and use these to approxima...
Preprint
Full-text available
In level co-creation an AI and human work together to create a video game level. One open challenge in level co-creation is how to empower human users to ensure particular qualities of the final level, such as challenge. There has been significant prior research into automated pathing and automated playtesting for video game levels, but not in how...
Preprint
Full-text available
Let's Plays of video games represent a relatively unexplored area for experimental AI in games. In this short paper, we discuss an approach to generate automated commentary for Let's Play videos, drawing on convolutional deep neural networks. We focus on Let's Plays of the popular game Minecraft. We compare our approach and a prior approach and dem...
Conference Paper
Full-text available
The ability to extract sequences of game events for high-resolution e-sport games has traditionally required access to the game's engine. This serves as a barrier to groups who don't possess this access. It is possible to apply deep learning to derive these logs from gameplay video, but it requires computational power that serves as an additional b...
Preprint
Full-text available
The ability to extract sequences of game events for high-resolution e-sport games has traditionally required access to the game's engine. This serves as a barrier to groups who don't possess this access. It is possible to apply deep learning to derive these logs from gameplay video, but it requires computational power that serves as an additional b...
Preprint
Full-text available
Machine learning has been applied to a number of creative, design-oriented tasks. However, it remains unclear how to best empower human users with these machine learning approaches, particularly those users without technical expertise. In this paper we propose a general framework for turn-based interaction between human users and AI agents designed...
Preprint
Full-text available
Machine learning advances have afforded an increase in algorithms capable of creating art, music, stories, games, and more. However, it is not yet well-understood how machine learning algorithms might best collaborate with people to support creative expression. To investigate how practicing designers perceive the role of AI in the creative process,...
Preprint
Full-text available
We introduce the problem of generating Let's Play-style commentary of gameplay video via machine learning. We propose an analysis of Let's Play commentary and a framework for building such a system. To test this framework we build an initial, naive implementation, which we use to interrogate the assumptions of the framework. We demonstrate promisin...
Preprint
Procedural content generation via Machine Learning (PCGML) is the umbrella term for approaches that generate content for games via machine learning. One of the benefits of PCGML is that, unlike search or grammar-based PCG, it does not require hand authoring of initial content or rules. Instead, PCGML relies on existing content and black box models,...
Preprint
Full-text available
Procedural Level Generation via Machine Learning (PLGML), the study of generating game levels with machine learning, has received a large amount of recent academic attention. For certain measures these approaches have shown success at replicating the quality of existing game levels. However, it is unclear the extent to which they might benefit huma...
Article
Automated game design has remained a key challenge within the field of Game AI. In this paper, we introduce a method for recombining existing games to create new games through a process called conceptual expansion.Prior automated game design approaches have relied on hand-authored or crowd-sourced knowledge, which limits the scope and applications...
Article
The ability to extract the sequence of game events for a given player's play-through has traditionally required access to the game's engine or source code. This serves as a barrier to researchers, developers, and hobbyists who might otherwise benefit from these game logs. In this paper we present two approaches to derive game logs from game video v...
Preprint
Full-text available
Automated game design has remained a key challenge within the field of Game AI. In this paper, we introduce a method for recombining existing games to create new games through a process called conceptual expansion. Prior automated game design approaches have relied on hand-authored or crowd-sourced knowledge, which limits the scope and applications...
Preprint
Full-text available
The ability to extract the sequence of game events for a given player's play-through has traditionally required access to the game's engine or source code. This serves as a barrier to researchers, developers, and hobbyists who might otherwise benefit from these game logs. In this paper we present two approaches to derive game logs from game video v...
Preprint
Full-text available
In this paper we present the Creative Invention Benchmark (CrIB), a 2000-problem benchmark for evaluating a particular facet of computational creativity. Specifically, we address combinational p-creativity, the creativity at play when someone combines existing knowledge to achieve a solution novel to that individual. We present generation strategie...
Article
Full-text available
Problems with few examples of a new class of objects prove challenging to most classifiers. One solution to is to reuse existing data through transfer methods such as one-shot learning or domain adaption. However these approaches require an explicit hand-authored or learned definition of how reuse can occur. We present an approach called conceptual...
Conference Paper
We present a novel approach to player modeling based on a convolutional neural net trained on game event logs. We test our approach and a hybrid extension over two distinct games, a clone of Super Mario Bros. and Gwario, a human computation version of Super Mario Bros.: The Lost Levels. We demonstrate high accuracy in predicting a variety of measur...

Network

Cited By