Matthew Guzdial

Dagmar Lukka Loftsdóttir, Matthew Guzdial

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 how objects move, and does not account for the stylistic movement often present in 2D animation. We propose a problem formulation that more closely adheres to the standard workflow of animation. We also demonstrate a model, SketchBetween, which learns to map between keyframes and sketched in-betweens to rendered sprite animations. We demonstrate that our problem formulation provides the required information for the task and that our model outperforms an existing method.

Akash Saravanan, Matthew Guzdial

Machine learning has had a great deal of success in image processing. However, the focus of this work has largely been on realistic images, ignoring more niche art styles such as pixel art. Additionally, many traditional machine learning models that focus on groups of pixels do not work well with pixel art, where individual pixels are important. We propose the Pixel VQ-VAE, a specialized VQ-VAE model that learns representations of pixel art. We show that it outperforms other models in both the quality of embeddings as well as performance on downstream tasks.

Kynan Sorochan, Matthew Guzdial

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 of designing units could help developers speed up the creation process as well as find new ideas. In this work we propose a method of generating balanced and useful RTS units. We draw on Search-Based PCG and a fitness function based on Monte Carlo Tree Search (MCTS). We present ten units generated by our system designed to be used in the game microRTS, as well as results demonstrating that these units are unique, useful, and balanced.

Emily Halina, Matthew Guzdial

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 individual designer. We evaluate our approach with a human subject study using a co-creative rhythm game design tool. We find that designers prefer our proposed method and produce higher quality content in comparison to an existing baseline.

Emily Halina, Matthew Guzdial

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 at each level of difficulty, a concept we refer to as "multidimensional" difficulty. In this paper, we introduce a diversity-based deep reinforcement learning approach for generating a set of agents of similar difficulty that utilize diverse strategies. We find this approach outperforms a baseline trained with specialized, human-authored reward functions in both diversity and performance.

Venkata Sai Revanth Atmakuri, Seth Cooper, Matthew Guzdial

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 game level blending to a limited number of annotated games. Even with annotated games, researchers often need to author an additional shared representation to make blending possible. In this paper, we present a novel approach to game level blending that employs Clustering-based Tile Embeddings (CTE), a learned level representation technique that can serve as a level representation for unannotated games and a unified level representation across games without the need for human annotation. CTE represents game level tiles as a continuous vector representation, unifying their visual, contextual, and behavioral information. We apply this approach to two classic Nintendo games, Lode Runner and The Legend of Zelda. We run an evaluation comparing the CTE representation to a common, human-annotated representation in the blending task and find that CTE has comparable or better performance without the need for human annotation.

Kristen K. Yu, Matthew Guzdial, Nathan Sturtevant

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. In the past, some AI Director studies have provided inconclusive results, so their effect on player experience is not clear. We take three AI Directors and directly compare them in a human subject study to test their effectiveness on quest selection. Our results show that a non-random AI Director provides a better player experience than a random AI Director.

Anahita Doosti, Matthew Guzdial

This paper investigates a combinational creativity approach to transfer learning to improve the performance of deep neural network-based models for music generation on out-of-distribution (OOD) genres. We identify Iranian folk music as an example of such an OOD genre for MusicVAE, a large generative music model. We find that a combinational creativity transfer learning approach can efficiently adapt MusicVAE to an Iranian folk music dataset, indicating potential for generating underrepresented music genres in the future.

Faraz Khadivpour, Arghasree Banerjee, Matthew Guzdial

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 responsible training example for a particular decision. This example can then be shown as an explanation: "this is what I (the AI) learned that led me to do that". We present experimental results across a number of domains along with the results of an Amazon Mechanical Turk user study, comparing responsibility and existing XAI methods on an image classification task. Our results demonstrate that responsibility can help improve accuracy for both human end users and secondary ML models.

Athar Mahmoudi-Nejad, Pierre Boulanger, Matthew Guzdial

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. This article proposes a virtual reality exposure therapy (VRET) platform capable of assessing a patient's mental state using non-intrusive and widely available physiological signals such as photoplethysmography (PPG). In a case study, we evaluate how PPG signals can be used to detect two binary classifications: peaceful and stressful states. Sixteen healthy subjects were exposed to the two VR environments (relaxed and stressful). Using LOSO cross-validation, our best classification model could predict the two states with a 70.6% accuracy which outperforms many more complex approaches.

Athar Mahmoudi-Nejad, Matthew Guzdial, Pierre Boulanger

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 specific anxiety responses. However, VRET approaches tend to require therapists to hand-select the appropriate spider for each patient, which is a time-consuming process and takes significant technical knowledge and patient insight. While automated methods exist, they tend to employ rules-based approaches with minimal ability to adapt to specific users. To address these challenges, we present a framework for VRET utilizing procedural content generation (PCG) and reinforcement learning (RL), which automatically adapts a spider to elicit a desired anxiety response. We demonstrate the superior performance of this system compared to a more common rules-based VRET method.

Emily Halina, Matthew Guzdial

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 in rules or functions, and PCGML typically requires significant training data, which may not be available early in development. In this paper, we introduce Tree-based Reconstructive Partitioning (TRP), a novel PCGML approach aimed to address this problem. Our results, across two domains, demonstrate that TRP produces levels that are more playable and coherent, and that the approach is more generalizable with less training data. We consider TRP to be a promising new approach that can afford the introduction of PCGML into the early stages of game development without requiring human expertise or significant training data.

Negar Mirgati, Matthew Guzdial

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 methods for obtaining such representations are laborious and time-consuming, which contributes to this problem. In this work, we aim to address this problem by utilizing gameplay videos of two human-annotated games to develop a novel multi-tail framework that learns to perform simultaneous level translation and generation. The translation tail of our framework can convert gameplay video frames to an equivalent secondary representation, while its generation tail can produce novel level segments. Evaluation results and comparisons between our framework and baselines suggest that combining the level generation and translation tasks can lead to an overall improved performance regarding both tasks. This represents a possible solution to limited annotated level data, and we demonstrate the potential for future versions to generalize to unseen games.

Mrunal Jadhav, Matthew Guzdial

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 levels unifying their visual, contextual and behavioural information. However, the original tile embedding struggled to generate levels with skewed tile distributions. For instance, Super Mario Bros. (SMB) wherein a majority of tiles represent the background. To remedy this, we present a modified tile embedding representation referred to as Clustering-based Tile Embedding (CTE). Further, we employ clustering to discretize the continuous CTE representation and present a novel two-step level generation to leverage both these representations. We evaluate the performance of our approach in generating levels for seen and unseen games with skewed tile distributions and outperform the original tile embeddings.

Akash Saravanan, Matthew Guzdial

A metagame is a collection of knowledge that goes beyond the rules of a game. In competitive, team-based games like Pokémon or League of Legends, it refers to the set of current dominant characters and/or strategies within the player base. Developer changes to the balance of the game can have drastic and unforeseen consequences on these sets of meta characters. A framework for predicting the impact of balance changes could aid developers in making more informed balance decisions. In this paper we present such a Meta Discovery framework, leveraging Reinforcement Learning for automated testing of balance changes. Our results demonstrate the ability to predict the outcome of balance changes in Pokémon Showdown, a collection of competitive Pokémon tiers, with high accuracy.

Natalie Bombardieri, Matthew Guzdial

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 tandem with localized level structure information. We test our approach on levels based on Super Mario Bros. (Infinite Mario Bros.) and Super Mario Bros.: The Lost Levels (Gwario), as well as original Super Mario Bros. levels. We outperform prior work, and demonstrate the utility of training on player logs, even when lacking them at test time for cross-domain player modelling.

Jalal Arabneydi, Saiful Islam, Srijita Das et al.

With the growing popularity of deep reinforcement learning (DRL), human-in-the-loop (HITL) approach has the potential to revolutionize the way we approach decision-making problems and create new opportunities for human-AI collaboration. In this article, we introduce a novel multi-layered hierarchical HITL DRL algorithm that comprises three types of learning: self learning, imitation learning and transfer learning. In addition, we consider three forms of human inputs: reward, action and demonstration. Furthermore, we discuss main challenges, trade-offs and advantages of HITL in solving complex problems and how human information can be integrated in the AI solution systematically. To verify our technical results, we present a real-world unmanned aerial vehicles (UAV) problem wherein a number of enemy drones attack a restricted area. The objective is to design a scalable HITL DRL algorithm for ally drones to neutralize the enemy drones before they reach the area. To this end, we first implement our solution using an award-winning open-source HITL software called Cogment. We then demonstrate several interesting results such as (a) HITL leads to faster training and higher performance, (b) advice acts as a guiding direction for gradient methods and lowers variance, and (c) the amount of advice should neither be too large nor too small to avoid over-training and under-training. Finally, we illustrate the role of human-AI cooperation in solving two real-world complex scenarios, i.e., overloaded and decoy attacks.

Dave Goel, Matthew Guzdial, Anurag Sarkar

World models are defined as a compressed spatial and temporal learned representation of an environment. The learned representation is typically a neural network, making transfer of the learned environment dynamics and explainability a challenge. In this paper, we propose an approach, Finite Automata Extraction (FAE), that learns a neuro-symbolic world model from gameplay video represented as programs in a novel domain-specific language (DSL): Retro Coder. Compared to prior world model approaches, FAE learns a more precise model of the environment and more general code than prior DSL-based approaches.

Md Saiful Islam, Srijita Das, Sai Krishna Gottipati et al.

Recent advances in reinforcement learning (RL) and Human-in-the-Loop (HitL) learning have made human-AI collaboration easier for humans to team with AI agents. Leveraging human expertise and experience with AI in intelligent systems can be efficient and beneficial. Still, it is unclear to what extent human-AI collaboration will be successful, and how such teaming performs compared to humans or AI agents only. In this work, we show that learning from humans is effective and that human-AI collaboration outperforms human-controlled and fully autonomous AI agents in a complex simulation environment. In addition, we have developed a new simulator for critical infrastructure protection, focusing on a scenario where AI-powered drones and human teams collaborate to defend an airport against enemy drone attacks. We develop a user interface to allow humans to assist AI agents effectively. We demonstrated that agents learn faster while learning from policy correction compared to learning from humans or agents. Furthermore, human-AI collaboration requires lower mental and temporal demands, reduces human effort, and yields higher performance than if humans directly controlled all agents. In conclusion, we show that humans can provide helpful advice to the RL agents, allowing them to improve learning in a multi-agent setting.

Anurag Sarkar, Matthew Guzdial, Sam Snodgrass et al.

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 motivated by a substantial number of recent PCG works that focus on generating novel content via repurposing derived knowledge. Such works have involved, for example, performing transfer learning on models trained on one game's content to adapt to another game's content, as well as recombining different generative distributions to blend the content of two or more games. Such approaches arose in part due to limitations in PCG via Machine Learning (PCGML) such as producing generative models for games lacking training data and generating content for entirely new games. In this paper, we categorize such approaches under this new lens of PCG-KT by offering a definition and framework for describing such methods and surveying existing works using this framework. Finally, we conclude by highlighting open problems and directions for future research in this area.

Athar Mahmoudi-Nejad, Matthew Guzdial, Pierre Boulanger

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-authored, pre-defined rules, which may not generalize to all individuals. In this paper, we propose an approach to automatically adapt therapeutic content to patients based on physiological measures. We implement our approach in the context of arachnophobia exposure therapy, and rely on experience-driven procedural content generation via reinforcement learning (EDPCGRL) to generate virtual spiders to match an individual patient. In this initial implementation, and due to the ongoing pandemic, we make use of virtual or artificial humans implemented based on prior arachnophobia psychology research. Our EDPCGRL method is able to more quickly adapt to these virtual humans with high accuracy in comparison to existing, search-based EDPCG approaches.

Matthew Guzdial, Nathan Sturtevant, Carolyn Yang

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 introduce a mixed-initiative tool employing Exhaustive PCG (EPCG) for puzzle level design to further explore mixed-initiative PCG. We run an online human subject study in which individuals use the tool with an EPCG component turned on or off. Our analysis of the results demonstrates that, although a majority of users did not prefer the tool, it made the level design process significantly easier, and that the tool impacted the subjects' design process. This paper describes the study results and draws lessons for mixed-initiative PCG tool design.

Kristen K. Yu, Matthew Guzdial, Nathan R. Sturtevant

Among academic communities there is no single agreed upon definition of a quest. The industry perspective on this topic is also largely unknown. Thus, thee 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 experience designing or implementing quests or narratives, and process the interviews using thematic analysis to identify trends. We identified a variety of personal developer definitions. However, we also discovered several themes that may inform future academic work. We introduce the definition-context-purpose paradigm as a synthesis of these trends: elements of a quest, purpose of a quest, and context of a quest. Finally, we discuss the developer's reaction to a recently proposed quest definition as part of a push towards a general quest definition.

Alexander Sieusahai, Matthew Guzdial

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 agent to an interpretable, percept-like input representation. We then train a surrogate model, which is itself interpretable, to replicate the behavior of the target, deep RL agent. Our experiments demonstrate that we can learn an effective surrogate that accurately approximates the underlying decision making of a target agent on a suite of Atari games.

Mrunal Jadhav, Matthew Guzdial

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 games exist, annotated datasets are curated only for a small handful. Thus current PLGML techniques have been explored in limited domains, with Super Mario Bros. as the most common example. To address this problem, we present tile embeddings, a unified, affordance-rich representation for tile-based 2D games. To learn this embedding, we employ autoencoders trained on the visual and semantic information of tiles from a set of existing, human-annotated games. We evaluate this representation on its ability to predict affordances for unseen tiles, and to serve as a PLGML representation for annotated and unannotated games.

Mohan Singamsetti, Anmol Mahajan, Matthew Guzdial

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, computational creativity-inspired transfer learning approach with neural architecture search. This approach finds models faster than naive architecture search via transferring existing weights to approximate the parameters of the new model. It outperforms standard transfer learning by allowing for the addition of features instead of only modifying existing features. We demonstrate that our approach outperforms standard neural architecture search and transfer learning methods in terms of efficiency, performance, and parameter counts on a variety of transfer learning tasks.

Zisen Zhou, Matthew Guzdial

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 and time-consuming process. In this work, we propose approximating human-AI interaction data and employing transfer learning to adapt learned co-creative knowledge from one game to a different game. We explore this approach for co-creative Zelda dungeon room generation.

Kynan Sorochan, Jerry Chen, Yakun Yu et al.

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 levels based on these paths. We extract player path data from gameplay video, train an LSTM to generate new paths based on this data, and then generate game levels based on this path data. We demonstrate that our approach leads to more coherent levels for the game Lode Runner in comparison to an existing PCGML approach.

Bowei Li, Ruohan Chen, Yuqing Xue et al.

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 generating \emph{Mega Man} levels. We conduct an initial investigation of our approach and evaluate it on measures of playability and stylistic similarity in comparison to a non-ensemble, existing Markov chain approach.

Nazanin Yousefzadeh Khameneh, Matthew Guzdial

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 reason for this is the lack of a consistent representation for dynamic game content, which is key for a number of statistical machine learning approaches. We present an autoencoder for deriving what we call "entity embeddings", a consistent way to represent different dynamic entities across multiple games in the same representation. In this paper we introduce the learned representation, along with some evidence towards its quality and future utility.

Adrian Gonzalez, Matthew Guzdial, Felix Ramos

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 and generate new game visuals based on their gameplay relevance. We test this approach with Pokémon sprites and Pokémon type information, since types are one of the game's core mechanics and they directly impact the game's visuals. Our experimental results indicate that adopting a transfer learning approach can help to improve visual quality and stability over unseen data.

Faraz Khadivpour, Matthew Guzdial

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 learning. This can be even more tricky in co-creative systems where human designers must interact with AI agents to generate game content. In this paper we present an approach to explainable artificial intelligence in which certain training instances are offered to human users as an explanation for the AI agent's actions during a co-creation process. We evaluate this approach by approximating its ability to provide human users with the explanations of AI agent's actions and helping them to more efficiently cooperate with the AI agent.

Matthew Guzdial, Devi Acharya, Max Kreminski et al.

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, expressive range analysis, and generative pipelines -- to key concepts in TTRPG design. We then discuss the implications of these relationships and suggest directions for future work uniting research in TTRPGs and PCG.

Matthew Guzdial, Mark Riedl

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 use these to approximate a search space of novel games. In a human subject study we demonstrate that these novel games are indistinguishable from human games in terms of challenge, and that one of the novel games was equivalent to one of the human games in terms of fun, frustration, and likeability.

Andrew Hoyt, Matthew Guzdial, Yalini Kumar et al.

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 to incorporate these into tools. In this demonstration we present an improvement of the Morai Maker mixed-initiative level editor for Super Mario Bros. that includes automated pathing and challenge approximation features.

Shukan Shah, Matthew Guzdial, Mark O. Riedl

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 demonstrate the generation of automated, artificial commentary.

Matthew Guzdial, Nicholas Liao, Jonathan Chen et al.

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, we developed a game level design tool for Super Mario Bros.-style games with a built-in AI level designer. In this paper we discuss our design of the Morai Maker intelligent tool through two mixed-methods studies with a total of over one-hundred participants. Our findings are as follows: (1) level designers vary in their desired interactions with, and role of, the AI, (2) the AI prompted the level designers to alter their design practices, and (3) the level designers perceived the AI as having potential value in their design practice, varying based on their desired role for the AI.

Matthew Guzdial, Shukan Shah, Mark Riedl

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 promising results towards future Let's Play commentary generation.

Matthew Guzdial, Nicholas Liao, Mark Riedl

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 human designers. In this paper we present a framework for co-creative level design with a PLGML agent. In support of this framework we present results from a user study and results from a comparative study of PLGML approaches.

Matthew Guzdial, Joshua Reno, Jonathan Chen et al.

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, which can be difficult to tune or tweak without expert knowledge. This is especially problematic when a human designer needs to understand how to manipulate their data or models to achieve desired results. We present an approach to Explainable PCGML via Design Patterns in which the design patterns act as a vocabulary and mode of interaction between user and model. We demonstrate that our technique outperforms non-explainable versions of our system in interactions with five expert designers, four of whom lack any machine learning expertise.

Zijin Luo, Matthew Guzdial, Nicholas Liao et al.

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 via convolutional neural networks and transfer learning. We evaluate the approaches in a Super Mario Bros. clone, Mega Man and Skyrim. Our results demonstrate our approach outperforms random forest and other transfer baselines.

Matthew Guzdial, Mark Riedl

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 of such systems. Our approach instead relies on machine learning to learn approximate representations of games. Our approach recombines knowledge from these learned representations to create new games via conceptual expansion. We evaluate this approach by demonstrating the ability for the system to recreate existing games. To the best of our knowledge, this represents the first machine learning-based automated game design system.

Matthew Guzdial, Nicholas Liao, Vishwa Shah et al.

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 strategies for the five problem categories of the benchmark and a set of initial baselines.

Matthew Guzdial, Mark O. Riedl

One of the defining characteristics of human creativity is the ability to make conceptual leaps, creating something surprising from typical knowledge. In comparison, deep neural networks often struggle to handle cases outside of their training data, which is especially problematic for problems with limited training data. Approaches exist to transfer knowledge from problems with sufficient data to those with insufficient data, but they tend to require additional training or a domain-specific method of transfer. We present a new approach, conceptual expansion, that serves as a general representation for reusing existing trained models to derive new models without backpropagation. We evaluate our approach on few-shot variations of two tasks: image classification and image generation, and outperform standard transfer learning approaches.

Adam Summerville, Sam Snodgrass, Matthew Guzdial et al.

This survey explores Procedural Content Generation via Machine Learning (PCGML), defined as the generation of game content using machine learning models trained on existing content. As the importance of PCG for game development increases, researchers explore new avenues for generating high-quality content with or without human involvement; this paper addresses the relatively new paradigm of using machine learning (in contrast with search-based, solver-based, and constructive methods). We focus on what is most often considered functional game content such as platformer levels, game maps, interactive fiction stories, and cards in collectible card games, as opposed to cosmetic content such as sprites and sound effects. In addition to using PCG for autonomous generation, co-creativity, mixed-initiative design, and compression, PCGML is suited for repair, critique, and content analysis because of its focus on modeling existing content. We discuss various data sources and representations that affect the resulting generated content. Multiple PCGML methods are covered, including neural networks, long short-term memory (LSTM) networks, autoencoders, and deep convolutional networks; Markov models, $n$-grams, and multi-dimensional Markov chains; clustering; and matrix factorization. Finally, we discuss open problems in the application of PCGML, including learning from small datasets, lack of training data, multi-layered learning, style-transfer, parameter tuning, and PCG as a game mechanic.

Matthew Guzdial, Mark Riedl

We present an approach to generate novel computer game levels that blend different game concepts in an unsupervised fashion. Our primary contribution is an analogical reasoning process to construct blends between level design models learned from gameplay videos. The models represent probabilistic relationships between elements in the game. An analogical reasoning process maps features between two models to produce blended models that can then generate new level chunks. As a proof-of-concept we train our system on the classic platformer game Super Mario Bros. due to its highly-regarded and well understood level design. We evaluate the extent to which the models represent stylistic level design knowledge and demonstrate the ability of our system to explain levels that were blended by human expert designers.

Matthew Guzdial, Mark Riedl

Algorithms that generate computer game content require game design knowledge. We present an approach to automatically learn game design knowledge for level design from gameplay videos. We further demonstrate how the acquired design knowledge can be used to generate sections of game levels. Our approach involves parsing video of people playing a game to detect the appearance of patterns of sprites and utilizing machine learning to build a probabilistic model of sprite placement. We show how rich game design information can be automatically parsed from gameplay videos and represented as a set of generative probabilistic models. We use Super Mario Bros. as a proof of concept. We evaluate our approach on a measure of playability and stylistic similarity to the original levels as represented in the gameplay videos.