Open-world games like Sable present expansive, virtual environments and use exploration of these environments as a central activity.How do players understand these worlds and organize their mental representations of their spaces?Kevin Lynch theorized that inhabitants of a city understand the "image" of that city in terms of five key elements: landmarks, paths, edges, nodes, and districts.We investigated whether Lynch's categories are also prominent in open-world game environments using thematic analysis of interviews in which players were asked to describe how they would navigate through these environments.We found that landmarks and edges feature prominently in players' responses, but paths, nodes, and districts are not emphasized as much.We also found that a sixth element type: "characters" stands out as a persistent theme in players' descriptions of these games.The addition of "characters" to Lynch's categories makes sense in virtual worlds, since the typical fixed routines of non-player characters (NPCs) make them more relevant to navigation than in the real world.

This talk describes a method for teaching recursion to intro-level students that the presenter has now been using for 3 semesters in his introductory CS labs, initially for students who were not successfully engaged by existing materials, and now as part of the standard materials on the topic. Notably, the method does NOT require any wishful thinking on the part of the student, and the presenter has found it to be anecdotally quite successful in allowing students who are stuck to solve recursive problems they had asked for help with. The method should work equally well for teaching induction.

Academic Procedural Content Generation research has until recently overlooked a significant real-world application of generative methods to existing games: game randomizers. These programs remix existing games by changing things like item locations, enemy stats, or even room connections to create a fresh experience based on a beloved game, and are especially popular among speedrunning and streaming communities. They generate where high-production-quality full-scale games, explicitly geared towards replay value. Randomizers fulfill many of the stated motivations of the academic PCG research community, and important new research directions can be developed by investigating this space.

Incremental procedural content generation (IPCG) has been used in games such as Minecraft to provide a unique flavor of gameplay, but requires that parts of the world can be generated independently of one another in any order and will always fit together in the end. Noise functions such as simplex noise are a very popular building block for IPCG systems, because they support this property, but noise functions alone have their limitations, one of which being an inability to create non-local structures or continuity. To combat this, noise functions are usually applied at several scales to provide fractal continuity and recognizable features similar to real world geography’s fractal complexity. This paper describes a system of fractal coordinates suitable for use with IPCG that generalize this idea of multiple layers of structure at different scales, and demonstrates how it can be used to achieve some interesting effects.

Pseudo-random number generators are ubiquitous components of content generation systems, because their outputs are difficult to predict but also repeatable given an initial seed. These properties make them especially useful as the basis for "random" decisions during a generative process, as they allow the process to be chaotic but also repeatable. This paper describes an open-source family of pseudo-random algorithms which allow for shuffling and distributing items in a reversible and incremental manner. To demonstrate the applicability of these algorithms, I show how they have been used in the creation of a word-search game which includes strong guarantees about the distribution of words that can be discovered.

Since virtual identities such as social media profiles and avatars have become a common venue for self-expression, it has become important to consider the ways in which existing systems embed the values of their designers. In order to design virtual identity systems that reflect the needs and preferences of diverse users, understanding how the virtual identity construction differs between groups is important. This paper presents a new methodology that leverages deep learning and differential clustering for comparative analysis of profile images, with a case study of almost 100 000 avatars from a large online community using a popular avatar creation platform. We use novelty discovery to segment the avatars, then cluster avatars by region to identify visual trends among low-and high-novelty avatars. We find that avatar customization correlates with increased social activity, and we are able to identify distinct visual trends among the U.S.-region and Japan-region profiles. Among these trends, realistic, idealistic, and creative self-representation can be distinguished. We observe that the realistic self-expression mirrors regional demographics, idealistic self-expression reflects shared mass-media tropes, and creative self-expression propagates within the communities.

Work on procedural content generation often centers game mechanics and visual/audio aesthetics, whereas the generation of social structures has not received the same attention, despite potentially enabling new forms of gameplay. When the generation of social and/or cultural content is attempted, tensions naturally arise between algorithmic efficiency realism, and representation. A specific algorithm for generating family trees is used as a case study for these issues, with the hope that this can stimulate broader discussion in the community.

Scott Turner's Minstrel is considered a landmark story-generation system, cited as an important system in our field's history for the quality of its output. Other influential systems such as Meehan's Tale-Spin have inspired modern successors, but although a few systems have followed Minstrel's case-based approach, none of them use its “imaginative recall” technique. This paper details Skald, a publicly-released rational reconstruction of Minstrel that enables exploration of Turner's work and discovery of new implications for future research. A key finding is a brittleness only hinted at in Turner's publications: the story library, story templates, and the recall system must be tailored to one another for Turner's original system to function. We show that this can be ameliorated through a number of techniques, however, from adding differential costs to transformations to removing the least-successful author-level actions. Another key finding is that Turner's original “boredom” system limited leverage of the story library. An alternative and its results are presented here. What emerges from this work is a different picture of the original Minstrel than that currently present in the literature, as well as a new system, Skald, that sets the stage for future research to explore Turner's ideas for story generation.

Scott Turner's 1993 Minstrel system was a high water mark in story generation, harnessing the concept of imaginative recall to generate creative stories. Using case-based reasoning and an author level planning system, Minstrel models human creative processes. However, the algorithmic and representational commitments made in Minstrel were never subject to principled and quantitative analysis. By rationally reconstructing Minstrel, we are able to investigate Turner's computational model of creativity and learn new lessons about his architecture. We find that Minstrel's original performance was tied to a well-groomed case library, but by modifying several components of the algorithm we can create a more general version which can construct stories using a sparser and less structured case library. Through a rational reconstruction of Minstrel, we both learn new architectural and algorithmic lessons about Minstrel’s computational model of creativity as well as make his architecture available to the contemporary research community for further experimentation.

The Level Generation Competition, part of the IEEE Computational Intelligence Society (CIS)-sponsored 2010 Mario AI Championship, was to our knowledge the world's first procedural content generation competition. Competitors participated by submitting level generators - software that generates new levels for a version of Super Mario Bros tailored to individual players' playing style. This paper presents the rules of the competition, the software used, the scoring procedure, the submitted level generators, and the results of the competition. We also discuss what can be learned from this competition, both about organizing procedural content generation competitions and about automatically generating levels for platform games. The paper is coauthored by the organizers of the competition (the first three authors) and the competitors.