Artificial intelligence (AI) has enabled agents to master complex video games, from first-person shooters likeCounter-Striketo real-time strategy games such asStarCraft IIand racing games likeGran Turismo. While these achievements are notable, applying these AI methods in commercial video game production remains challenging due to computational constraints. In commercial scenarios, the majority of computational resources are allocated to 3D rendering, leaving limited capacity for AI methods, which often demand high computational power, particularly those relying on pixel-based sensors. Moreover, the gaming industry prioritizes creating human-like behavior in AI agents to enhance player experience, unlike academic models that focus on maximizing game performance. This paper introduces a novel methodology for training neural networks via imitation learning to play a complex, commercial-standard, VALORANT-like 2v2 tactical shooter game, requiring only modest CPU hardware during inference. Our approach leverages an innovative, pixel-free perception architecture using a small set of ray-cast sensors, which capture essential spatial information efficiently. These sensors allow AI to perform competently without the computational overhead of traditional methods. Models are trained to mimic human behavior using supervised learning on human trajectory data, resulting in realistic and engaging AI agents. Human evaluation tests confirm that our AI agents provide human-like gameplay experiences while operating efficiently under computational constraints. This offers a significant advancement in AI model development for tactical shooter games and possibly other genres.

Similarity estimation is essential for many game AI applications, from the procedural generation of distinct assets to automated exploration with game-playing agents. While similarity metrics often substitute human evaluation, their alignment with our judgement is unclear. Consequently, the result of their application can fail human expectations, leading to e.g. unappreciated content or unbelievable agent behaviour. We alleviate this gap through a multi-factorial study of two tile-based games in two representations, where participants (N=456) judged the similarity of level triplets. Based on this data, we construct domain-specific perceptual spaces, encoding similarity-relevant attributes. We compare 12 metrics to these spaces and evaluate their approximation quality through several quantitative lenses. Moreover, we conduct a qualitative labelling study to identify the features underlying the human similarity judgement in this popular genre. Our findings inform the selection of existing metrics and highlight requirements for the design of new similarity metrics benefiting game development and research.

In this 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 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, such as producing generative models for games lacking training data and generating content for entirely new games. In this article, 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.

Optimizing operations on critical infrastructure networks is key to reducing the impact of disruptive events. In this paper, we explore the potential of having humans and algorithms work together to address this difficult task. For this purpose, we use a gamified experiment to build and assess this potential in the context of the debris collection problem (i.e., “gamesploring”). We developed a digital game where players can request the help of the computer while facing a multi-objective problem of assigning contractors to road segments for clearing debris in a disaster area. Through a within-subjects experimental study, we assessed how players optimized under various circumstances (e.g., initial solution vs. from scratch) compared to the computer on its own. The results are both surprising as well as insightful: they suggest that human-machine collaboration is indeed beneficial but also that more work is needed on how to appropriately guide this form of collaboration.

Agent-based simulations are widely used for modeling human behavior in various contexts. However, such simulations may oversimplify human decision-making. We propose the use of Gamettes to extract rich data on human decision-making and help in improving the human behavioral aspects of models underlying agent-based simulations. We show how Gamettes are designed and provide empirical validation for using Gamettes in an experimental supply chain setting to study human decision-making. Our results show that Gamettes are successful in capturing the expected behaviors and patterns in supply chain decisions, and, thus, we find evidence for the capability of Gamettes to inform behavioral models.

Recent procedural content generation via machine learning (PCGML) methods allow learning from existing content to produce similar content automatically. While these approaches are able to generate content for different games (e.g. Super Mario Bros., DOOM, Zelda, and Kid Icarus), it is an open question how well these approaches can capture large-scale visual patterns such as symmetry. In this paper, we propose match-three games as a domain to test PCGML algorithms regarding their ability to generate suitable patterns. We demonstrate that popular algorithms such as Generative Adversarial Networks struggle in this domain and propose adaptations to improve their performance. In particular, we augment the neighbourhood of a Markov Random Fields approach to take into account not only local but also symmetric positional information. We conduct several empirical tests, including a user study that show the improvements achieved by the proposed modifications and obtain promising results.

Procedural content generation via machine learning (PCGML) has demonstrated its usefulness as a content and game creation approach, and has been shown to be able to support human creativity. An important facet of creativity is combinational creativity or the recombination, adaptation, and reuse of ideas and concepts between and across domains. In this paper, we present a PCGML approach for level generation that is able to recombine, adapt, and reuse structural patterns from several domains to approximate unseen domains. We extend prior work involving example-driven Binary Space Partitioning for recombining and reusing patterns in multiple domains, and incorporate Variational Autoencoders (VAEs) for generating unseen structures. We evaluate our approach by blending across 7 domains and subsets of those domains. We show that our approach is able to blend domains together while retaining structural components. Additionally, by using different groups of training domains our approach is able to generate both 1) levels that reproduce and capture features of a target domain, and 2) levels that have vastly different properties from the input domain.

Computational thinking (CT) is key to digital literacy and helps develop problem-solving skills, which are fundamental in modern school. As game design shows potential for teaching CT, metrics like Dr. Scratch emerge that help scholars systematically assess the CT of student-designed games, particularly with Scratch. Compared to other CT metrics, Dr. Scratch scores the CT of Scratch projects automatically and can be used to describe CT development. However, previous research using Dr. Scratch summatively assessed CT, but did not look at CT development. We use Dr. Scratch to assess the CT development of Scratch games designed by 8th-grade students in STEM curricula. We show how CT proficiency in student-designed games develops differently in each CT dimension, where parallelism, synchronization, and logic develop proficiently, while developing abstraction seems hard. We discuss insights into game-based CT development for STEM, and suggest improvements for metric-based CT assessment.

Gamification and serious games have the capacity to increase engagement in often non-engaging contexts such as a test. In this study, we gamified a psychological test, the Thematic Apperception Test (TAT), with the player motivation concepts of achievement, exploration, and social interactions. We used the platform Study-Crafter to implement our games and ran a study to test the effectiveness of this gamified psychological assessment. All participants completed both the standard version of the TAT and our gamified versions and rated their experience in each setting through self-reports. Our results show that the gamified versions of the TAT provided a more enjoyable and motivating experience than the standard version. We conclude that gamifying psychological tests has potential for increasing motivation in psychological assessments while questions of validity remain to be addressed.

Interactivity and player experience are inextricably entwined with the creation of compelling narratives for interactive digital media. Narrative shapes and buttresses many such experiences, and therefore designers must construct compelling narrative arcs while carefully considering the effects of interaction on both the story and the player. As the narrative becomes more structurally complex, due to choice-based branching and other player actions, designers need to employ commensurately capable models and visualizations to keep track of that growing complexity. However, previous models of interactive narrative have failed to fully capture interactive elements with automated, operationalized visualizations. In this paper, we describe an algorithm for automated construction of a framework-driven, graph-based representation of interactive narrative. This representation more fully and transparently models structural and interactive features of the narrative than did prior approaches. We present an initial evaluation of this representation, based on modified cognitive walkthroughs performed by interactive narrative design and research experts from our research team, and we describe the takeaways for future improvement on interactive narrative modeling and analysis.

This paper presents steps towards a generalized player model built around an external personalization and design framework. The external framework, the Player, Environment, Agents, System (PEAS) framework, resulted from a broad scope review of the personalization, player modeling, and game design literature. Leveraging this framework allows us to define a mapping from existing player and personality models to a uniform representation of player preferences over game components. We present our pipeline for developing a generalized player model from these existing models, how to translate and blend them, and finally how to use the blended model for recommending and personalizing games. We follow up the presentation of our pipeline with an extended example to highlight how two existing player modeling approaches can be combined into a singular model, and how that blended model can be used.

Personalization has been explored in the context of games in many forms (e.g., dynamic difficulty adjustment, affective video games, adaptive systems, experience-driven PCG, etc.). The majority of techniques used in these fields have relied on data-driven or manual methods for identifying game components to modify for personalization. We propose a theoretical framework for identifying and categorizing low-level components of games that can be personalized. In this paper we first perform a review of game design frameworks and personalization approaches. We then systematically identify the aspects of games which have been utilized for personalization and which components have been identified in game design frameworks as building blocks of games. We synthesize the identified components into categories of game elements. We then propose PEAS, a theoretical framework for personalization through the adaptation of the Player, Environment, Agents, and System.

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, cocreativity, 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 generated content. Multiple PCGML methods are covered, including neural networks: long short-term memory 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 PCGML, including learning from small data sets, lack of training data, multilayered learning, style-transfer, parameter tuning, and PCG as a game mechanic.

Evaluating the output of content generators is still one of the key open research challenges in Procedural Content Generation (PCG). This paper presents a collection of metrics for evaluating the quality of platform game levels, and analyzes how well these metrics are able to capture the human-perceived difficulty, visual aesthetics and enjoyment of these levels. We show empirically, in the context of Infinite Mario Bros (IMB), that some of the proposed metrics yield correlation values with human ratings that are near empirical upper bounds derived from a human inter-rater agreement study. We also show that a simple linear regression model using a subset of our metrics as input features is able to substantially outperform a previous approach that uses a neural network for predicting human-perceived difficulty, visual aesthetics, and enjoyment in IMB levels.

The use of statistical and machine learning approaches, such as Markov chains, for procedural content generation (PCG) has been growing in recent years in the field of Game AI. However, there has been little work in learning to generate content, specifically levels, accounting for player movement within those levels. We are interested in extracting player models automatically from play traces and using those learned models, paired with a machine learning-based generator to create levels that allow the same types of movements observed in the play traces. We test our approach by generating levels for Super Mario Bros. We compare our results against the original levels, a previous constrained sampling approach, and a previous approach that learned a combined player and level model.

Procedural content generation has become a popular research topic in recent years. However, most content generation systems are specialized to a single game. We are interested in methods that can generate content for a wide variety of games without a game-specific algorithm design. Statistical approaches are a promising avenue for such generators and, more specifically, map generators. In this paper, we explore Markov models as a means of modeling and generating content for multiple domains. We apply our Markov models to Super Mario Bros., Loderunner , and Kid Icarus in order to determine how well our models perform in terms of the playability of the content generated, the expressive ranges of the models, and the effects of training data on those expressive ranges.