Hundreds of millions of people play computer games every day For them, game content—from 3D objects to abstract puzzles—plays a major entertainment role Manual labor has so far ensured that the quality and quantity of game content matched the demands of the playing community, but is facing new scalability challenges due to the exponential growth over the last decade of both the gamer population and the production costs Procedural Content Generation for Games (PCG-G) may address these challenges by automating, or aiding in, game content generation PCG-G is difficult, since the generator has to create the content, satisfy constraints imposed by the artist, and return interesting instances for gamers Despite a large body of research focusing on PCG-G, particularly over the past decade, ours is the first comprehensive survey of the field of PCG-G We first introduce a comprehensive, six-layered taxonomy of game content: bits, space, systems, scenarios, design, and derived Second, we survey the methods used across the whole field of PCG-G from a large research body Third, we map PCG-G methods to game content layers; it turns out that many of the methods used to generate game content from one layer can be used to generate content from another We also survey the use of methods in practice, that is, in commercial or prototype games Fourth and last, we discuss several directions for future research in PCG-G, which we believe deserve close attention in the near future

Procedural content generation for games: A survey

Artificial Intelligence (AI) plays an increasingly important role in improving HCI and user experience. Yet many challenges persist in designing and innovating valuable human-AI interactions. For example, AI systems can make unpredictable errors, and these errors damage UX and even lead to undesired societal impact. However, HCI routinely grapples with complex technologies and mitigates their unintended consequences. What makes AI different? What makes human-AI interaction appear particularly difficult to design? This paper investigates these questions. We synthesize prior research, our own design and research experience, and our observations when teaching human-AI interaction. We identify two sources of AI's distinctive design challenges: 1) uncertainty surrounding AI's capabilities, 2) AI's output complexity, spanning from simple to adaptive complex. We identify four levels of AI systems. On each level, designers encounter a different subset of the design challenges. We demonstrate how these findings reveal new insights for designers, researchers, and design tool makers in productively addressing the challenges of human-AI interaction going forward.

https://dl.acm.org/doi/pdf/10.1145/3313831.3376301

Re-examining Whether, Why, and How Human-AI Interaction Is Uniquely Difficult to Design

Story generation is the problem of automatically selecting a sequence of events that meet a set of criteria and can be told as a story. Story generation is knowledge-intensive; traditional story generators rely on a priori defined domain models about fictional worlds, including characters, places, and actions that can be performed. Manually authoring the domain models is costly and thus not scalable. We present a novel class of story generation system that can generate stories in an unknown domain. Our system (a) automatically learns a domain model by crowdsourcing a corpus of narrative examples and (b) generates stories by sampling from the space defined by the domain model. A large-scale evaluation shows that stories generated by our system for a previously unknown topic are comparable in quality to simple stories authored by untrained humans.

/pdf/story-generation-with-crowdsourced-plot-graphs-3wg7bkth37.pdf

Story generation with crowdsourced plot graphs

Procedural content generators for games produce artifacts from a latent design space. This space is often only implicitly defined, an emergent result of the procedures used in the generator. In this paper, we outline an approach to content generation that centers on explicit description of the design space, using domain-independent procedures to produce artifacts from the described space. By concisely capturing a design space as an answer set program, we can rapidly define and expressively sculpt new generators for a variety of game content domains. We walk through the reimplementation of a reference evolutionary content generator in a tutorial example, and review existing applications of answer set programming to generative-content design problems in and outside of a game context.

/pdf/answer-set-programming-for-procedural-content-generation-a-4lbtmyvywv.pdf

Answer Set Programming for Procedural Content Generation: A Design Space Approach

Computers are often used as tools to design, implement, and even visualize a variety of narrative forms. Many researchers and artists are now further attempting to engage the computer actively throughout the development of the narrative itself. Any form of computational narrative authoring is at some level always mixed-initiative , meaning that the processing capabilities of the computer are utilized with a varying degree to automate certain features of the authoring process. We structure this survey by focusing on two key components of stories, plot and space , and more specifically the degree to which these are either automated by the computer or authored manually . By examining the successes of existing research, we identify potential new research directions in the field of computational narrative. We also identify the advantages of developing a standard model of narrative to allow for collaboration between plot and space automation techniques. This would likely benefit the field of automated space generation with the strengths in the field of automated plot generation.

/pdf/a-survey-on-story-generation-techniques-for-authoring-3kad5zl1wg.pdf

A Survey on Story Generation Techniques for Authoring Computational Narratives

Creative generative machine learning interfaces are stronger when multiple actors bearing different points of view actively contribute to them. User experience (UX) research and design involvement in the creation of machine learning (ML) models help ML research scientists to more effectively identify human needs that ML models will fulfill. The People and AI Research (PAIR) group within Google developed a novel program method in which UXers are embedded into an ML research group for three months to provide a human-centered perspective on the creation of ML models. The first full-time cohort of UXers were embedded in a team of ML research scientists focused on deep generative models to assist in music composition. Here, we discuss the structure and goals of the program, challenges we faced during execution, and insights gained as a result of the process. We offer practical suggestions for how to foster communication between UX and ML research teams and recommended UX design processes for building creative generative machine learning interfaces.

Identifying the Intersections: User Experience + Research Scientist Collaboration in a Generative Machine Learning Interface

A drama manager (DM) monitors an interactive experience, such as a computer game, and intervenes to shape the global experience so that it satisfies the author's expressive goals without decreasing a player's interactive agency. Most research on drama management has proposed AI architectures and provided abstract evaluations of their effectiveness; a smaller body of work has also evaluated the effect of drama management on player experience. Little attention has been paid, however, to evaluating the authorial leverage provided by a drama-management architecture: determining, for a given architecture, the additional non-linear story complexity a drama manager affords over traditional scripting methods. In this paper, we propose three criteria for evaluating the authorial leverage of a DM: 1) the script-and-trigger complexity of the DM story policy; 2) the degree of policy change given changes to story elements; and 3) the average story branching factor for DM policies versus script-and-trigger policies for stories of equivalent quality. We apply these criteria to declarative optimization-based drama management (DODM) by using decision tree learning to capture equivalent trigger logic, and show that DODM does in fact provide authorial leverage.

/pdf/evaluating-the-authorial-leverage-of-drama-management-596xaa2mea.pdf

Evaluating the authorial leverage of drama management

Often, video game designers must choose between creating a restrictive, linear experience and designing an open world with many different story lines that fail to form a tightly crafted narrative arc A drama manager (DM) can provide a solution to this dilemma A DM monitors an interactive experience, such as a computer game, and intervenes to shape the global experience so that it satisfies the author’s expressive goals without decreasing a player’s interactive agency Previous work with declarative optimization-based drama management (DODM) has focused on simulated player studies in abstract game worlds In this paper, we present the integration of DODM into a real-time adventurestyle dungeon game called EMPath We describe the game world as well as the modifications that had to be made to the DM as the result of integrating with a concrete, playable experience These changes include the development of new story evaluation features, improving drama management move refiners and creating a new player model We also describe the results of a play test comparing player experiences with the drama manager on and off

/pdf/from-abstraction-to-reality-integrating-drama-management-1xanhpx9io.pdf

From Abstraction to Reality: Integrating Drama Management into a Playable Game Experience

RoleModel is a novel story generator organized around explicit formal models of character roles. RoleModel expands the expressiveness of stories generated from arbitrary partial domain specification by using a formal model of roles within an abductive logic programming framework. Authorial goals in the system can be fully or partially specified as constraints in an abductive logic program. In particular, the RoleModel system focuses on representing and satisfying role constraints of the story characters. This paper discusses the basic architecture for the RoleModel approach, demonstrates example output from the system through three use-cases, discusses the authorial expressiveness enabled by a "stageless" abductive logic approach to story generation, and proposes the current and future directions.

/pdf/rolemodel-towards-a-formal-model-of-dramatic-roles-for-story-daymv0h2bv.pdf

RoleModel: towards a formal model of dramatic roles for story generation

Often, video game designers must choose between creating a linear experience, and designing an open world with many different story lines that fail to form a tightly crafted narrative arc. A drama manager (DM) can provide a solution to this dilemma. A DM monitors an interactive experience, such as a computer game, and intervenes to shape the global experience so that it satisfies the author's expressive goals without decreasing a player's interactive agency. In this demo we present the first integration of declarative optimization-based drama management (DODM) into an adventure-style dungeon game called EMPath.

/pdf/integrating-drama-management-into-an-adventure-game-52evce5xup.pdf

Sherol Chen

Papers

Identifying the Intersections: User Experience + Research Scientist Collaboration in a Generative Machine Learning Interface

Evaluating the authorial leverage of drama management

From Abstraction to Reality: Integrating Drama Management into a Playable Game Experience

RoleModel: towards a formal model of dramatic roles for story generation

Integrating drama management into an adventure game