Figure 1 - uploaded by Anne M Sullivan
Content may be subject to copyright.
This diagram illustrates the process of AI-based game design. The AI system affords certain mechanics and aesthetics for the game design, while the game design provides the context in which the AI operates. Domain information, such as theories.
Source publication
With the current set of design tools and methods available to game designers, vast portions of the space of possible games are not currently reachable. In the past, technological advances such as improved graphics and new controllers have driven the creation of new forms of gameplay, but games have still not made great strides into new gameplay exp...
Context in source publication
Context 1
... we describe the process of AI-based game design (see Figure 1) within the context of five AI-based games and their associated AI systems, each of which is under development by one of the authors. 1. Pataphysic Institute is a multiplayer game in which the AI architecture, known as the Mind Module , gives both avatars and non-player characters personalities, moods and emotions (Eladhari 2010). Players need to defeat manifestations of negative mental states by cooperating — the spells they can cast depend on their personalities and states of mind. 2. Mind Music is a small experimental game in adaptive music which also uses the Mind Module . In the game, state of mind is expressed by variations in harmony, groove and melodies (Eladhari et al. 2006). 3. Rathenn 1 is a 2D platformer game in which the player influences the creation of a procedurally generated level while they are exploring it. The player influences the game by climbing ladders that push the level towards particular extremes of the generative space. Rathenn uses the Launchpad rhythm-based procedural level generator to choose small segments of a level, called rhythm groups, as players continue exploring (Smith et al. 2011). 4. Prom Week 2 is a social simulation game about the dramatic week leading up to a high school prom, in which players sculpt the social landscape by having characters engage in social exchanges with each other. Comme il Faut (CiF) is the supporting AI system that enables an interactive, authorable model of social interaction for autonomous agents (McCoy et al. 2010). 5. Mismanor is a role-playing game in which the core mechanic is social interaction instead of combat, with a focus on supporting player-driven story. It uses both a modified version of the CiF framework (mentioned above) to handle game-level social interactions, and GrailGM to manage the story structure and quest system (Sullivan et al. ...
Similar publications
Ludii is a new general game system, currently under development, which aims to support a wider range of games than existing systems and approaches. It is being developed primarily for the task of game design, but offers a number of other potential benefits for game and AI researchers, professionals and hobbyists. This paper is based on an interacti...
This article explores the design and instructional effectiveness of
Medulla, an educational game meant to teach brain structure and
function to undergraduate psychology students. Developed in
the retro-style platformer genre, Medulla uses two-dimensional
gameplay with pixel-based graphics to engage students in
learning content related to the brain,...
We conducted an experiment where participants played a perfect-information game against a computer, which was programmed to deviate often from its backward induction strategy right at the beginning of the game. Participants knew that in each game, the computer was nevertheless optimizing against some belief about the participant's future strategy....
There have been several attempts in recent years to develop a remote communication device using sensory modalities other than speech that would induce a user’s positive experience with his/her conversation partner. Specifically, Hugvie is a human-shaped pillow as well as a remote communication device enabling users to combine a hugging experience w...
Citations
... Automated game design [24], [25] is one of the core themes in the field of game AI. As AI technology rapidly advances, various aspects of how AI can be utilized in automated game design have been discussed, including the design process [26], design patterns [27], and creative machine learning [28]. Several studies [29], [30] propose methods to generate a game by integrating multiple elements such as visuals, audio, narrative, levels, rules, and gameplay. ...
To lower the barriers to game design development, automated game design, which generates game designs through computational processes, has been explored. In automated game design, machine learning-based techniques such as evolutionary algorithms have achieved success. Benefiting from the remarkable advancements in deep learning, applications in computer vision and natural language processing have progressed in level generation. However, due to the limited amount of data in game design, the application of deep learning has been insufficient for tasks such as game description generation. To pioneer a new approach for handling limited data in automated game design, we focus on the in-context learning of large language models (LLMs). LLMs can capture the features of a task from a few demonstration examples and apply the capabilities acquired during pre-training. We introduce the grammar of game descriptions, which effectively structures the game design space, into the LLMs' reasoning process. Grammar helps LLMs capture the characteristics of the complex task of game description generation. Furthermore, we propose a decoding method that iteratively improves the generated output by leveraging the grammar. Our experiments demonstrate that this approach performs well in generating game descriptions.
... GenAI creates new content, while conventional AI may also generates some simple content like labels or paths, genAI focuses on producing highdimensional data like text, conversations or images. (Zhang et al. 2023) This evolution aligns with the previously discussed AIbased game, which defines games as being "designed around AI" (Treanor et al. 2015) or as having "an AI system deeply integrated into their core mechanics and aesthetics" (Eladhari et al. 2011). However, the AI discussed in these studies often encompasses a broader spectrum, including elements like the physics simulation in Super Mario Bros, Go AI, and more. ...
Generative AI (GenAI), encompassing image generation and large language models (LLMs), has opened new avenues for gameplay experiences. This paper introduces "1001 Nights", a narrative game centered on GenAI. Drawing inspiration from Wittgenstein's note, "The limits of my language mean the limits of my world", the game exemplifies the concept of language as reality. The protagonist, Shahrzad, possesses a unique power: specific keywords, such as "sword" or "shield", when spoken by others in tales, materialize as tangible weapons, serving as battle equipment against the King. Players guide the LLM-driven King in co-creating narratives, with GPT-4 employing LLM reasoning methods to ensure story consistency. As these narratives progress, the depicted world is dynamically generated and visualized through Stable Diffusion, blurring the boundaries between narrative and in-game reality. This fusion of interactive storytelling combines gameplay paradigms and story together with dynamic content generation. Players not only aim to alter Shahrzad's fate from the original folklore, but also leverage the power of natural language to shape the game's world. With this example, we propose the term "AI-Native games" to categorize innovative games where GenAI is fundamental to the game's novel mechanics and very existence.
... GenAI creates new content, while conventional AI may also generates some simple content like labels or paths, genAI focuses on producing highdimensional data like text, conversations or images. (Zhang et al. 2023) This evolution aligns with the previously discussed AIbased game, which defines games as being "designed around AI" (Treanor et al. 2015) or as having "an AI system deeply integrated into their core mechanics and aesthetics" (Eladhari et al. 2011). However, the AI discussed in these studies often encompasses a broader spectrum, including elements like the physics simulation in Super Mario Bros, Go AI, and more. ...
In this paper, we present "1001 Nights", an AI-native game that allows players lead in-game reality through co-created storytelling with the character driven by large language model. The concept is inspired by Wittgenstein's idea of the limits of one's world being determined by the bounds of their language. Using advanced AI tools like GPT-4 and Stable Diffusion, the second iteration of the game enables the protagonist, Shahrzad, to realize words and stories in her world. The player can steer the conversation with the AI King towards specific keywords, which then become battle equipment in the game. This blend of interactive narrative and text-to-image transformation challenges the conventional border between the game world and reality through a dual perspective. We focus on Shahrzad, who seeks to alter her fate compared to the original folklore, and the player, who collaborates with AI to craft narratives and shape the game world. We explore the technical and design elements of implementing such a game with an objective to enhance the narrative game genre with AI-generated content and to delve into AI-native gameplay possibilities.
... Request permissions from permissions@acm.org. [7], which now includes the player perspective via player-AI interaction (PAI) design. The AI affords certain mechanics to the game, while the game design provides the context for which the AI operates. ...
... The game research community has developed various guidelines to help game designers explore new gameplay experiences based on AI innovation [7,32,38,52]. This work is commonly developed by examining how AI is used in several existing games [38,52] or distilled from reflecting on the design process of AI-based games under development [1,7,32]. ...
... The game research community has developed various guidelines to help game designers explore new gameplay experiences based on AI innovation [7,32,38,52]. This work is commonly developed by examining how AI is used in several existing games [38,52] or distilled from reflecting on the design process of AI-based games under development [1,7,32]. For example, Eladhari et al. [7] describe a standard process for designing games where the AI system is a core part of the game's design through reflections on the decisions made in various games that the authors were developing. ...
... The TOG approach is informed by work reflecting on processes in AI-based game design (AIGD) (Eladhari et al. 2011). In this context, it is crucial to recognize that game creation is, fundamentally a liberal art, even when taught within the engineering disciplines. ...
... In short, AI-based game design is the creation of games where the game mechanics are intertwined with the AI systems used to realize the game. Examining design process in making AI-based games, Eladhari et al. (2011) identified distinct processes in that approach by means of case studies. The authors also found that a common denominator in the practice was to consider the respective knowledge domains in triplets, e.g. ...
This paper describes an approach to facilitate innovation in game design by increasing the designers’ palette of playable and participatory computational expressions. The TOG model (Technology, Ontology, and Game Genre) can be used in teaching game design and related practices, but is also applicable to prototyping in professional settings. TOG is inspired by the processes of AI-based game design, and introduces the concept of the techno-artistic minimum. It was conceptualized when teaching a course on computational expression at Malta University. The main aim for teaching with the TOG model was to facilitate innovation by challenging aspiring game designers to think ‘outside the box’ and come up with unusual and innovate creative solutions. In addition, TOG can complement existing design methods such as MDA and DDT in the practice of professional game designers.
... If the NPC is designed to be competitive, the clash between the player and the NPC creates a dramatic interactive experience about the interplay between power, strategy, and wit (Riedl et al. 2011). The more the NPC portrays itself as, and behaves like, a sentient organism, the more the player will enjoy being the victor of this challenge (Eladhari et al. 2011). However, different AI methods suffuse the NPCs with different degrees of intelligence. ...
... Moreover, it facilitates the recognition of areas of the design space that as of yet remain unexplored, providing inspiration to create experiences that break new ground. This work in turn is inspired by taxonomies of other domains (Bartle 2004;Warpefelt and Verhagen 2015) and proposals for future directions of AI-based game design (Eladhari et al. 2011;Horswill 2014;Treanor et al. 2015). ...
Computationally assisted performance is a burgeoning area for AI applications, and an important stepping stone toward the dream of generative and personalized narrative experiences. As more pieces of computationally assisted performance are developed, it will become ever more important to develop a vocabulary with which to describe them. Inspired by previous work in creating taxonomies for other related domains, this paper outlines a taxonomy for performance-based experiences, drawn from digital games, traditional theatre, and the hybrid of the two. Having such a taxonomy not only creates a common language with which to discuss such experiences, but reveals unexplored design space in the field, and the particular applications of artificial intelligence necessary to realize them.
... WAWLT represents an example of AI-based game design [6] inspired by the study of existing player storytelling practices [5,12] in simulation-driven games. In designing WAWLT, we set out to provide creativity support features that would help players overcome four major barriers to creativity documented in [13]: fear of the blank canvas; fear of judgment; writer's block; and perfectionism. ...
... By allowing players to control aspects of content generation through game mechanics, they are able to form strategies around content generation, making gameplay revolve around it. [6,25] However, binding content generation to game mechanics causes design challenges for both game design and AI design as the act of designing games shifts from hand authoring player experiences to creating ranges of meaningful content with algorithms [25]. The challenge in content generation remains to produce content that is both novel and valuable, matching the design task at hand [3,19,32]. ...
... PCG-based games can be challenging to prototype as their core gameplay, per definition [25], revolves around content generation. Instead of designing the game and its AI system in vacuum, the design phases are tightly coupled through the context provided by game design -in which the AI system's decisions need to make sense in -and the affordances based on the AI system's capabilities that would otherwise be unattainable [6,25]. However, disjointed context and affordances can result in catastrophic failures [16] that leave the game in an unplayable state and result in a greater overall development effort. ...
... Early iterations are encouraged as both design activities need to be fleshed out as they feed each other. [6,25] PCG systems afford unique game dynamics when leveraged to a high enough degree [22] and can lead to a new way of playing games or to new game genres [6]. However, in order to leverage PCG to its full degree, the AI being utilized must support player exploration without merely creating an illusion of intelligence. ...
... To alleviate this, we propose an automated analysis and visualization system to serve as an intermediate step between initial design and playtesting. In software design, automated analysis and visualization have proven effective for design analysis and improvement [48], and some researchers have called for the use of automated methods to augment the iterative design process in games [16]. We believe that such a paradigm shift could similarly improve interactive narrative design methods. ...
