Game development is a highly technical practice that traditionally requires programming skills. This serves as a barrier to entry for would-be developers or those hoping to use games as part of their creative expression. While there have been prior game development tools focused on accessibility, they generally still require programming, or have major limitations in terms of the kinds of games they can make. In this paper we introduce Mechanic Maker, a tool for creating a wide-range of game mechanics without programming. It instead relies on a backend symbolic learning system to synthesize game mechanics from examples. We conducted a user study to evaluate the benefits of the tool for participants with a variety of programming and game development experience. Our results demonstrated that participants' ability to use the tool was unrelated to programming ability. We conclude that tools like ours could help democratize game development, making the practice accessible regardless of programming skills.

Last year, 18 percent of Stanford University seniors graduated with a degree in computer science, more than double the proportion of just a decade earlier. Over the same period at MIT, that rate went up from 23 percent to 42 percent. These increases are common everywhere: The average number of undergraduate CS majors at universities in the U.S. and Canada tripled in the decade after 2005, and it keeps growing. Students' interest in CS is intellectual--culture moves through computation these days--but it is also professional. Young people hope to access the wealth, power, and influence of the technology sector. That ambition has created both enormous administrative strain and a competition for prestige.

Genie often adds this effect to the games it generates. While Genie is an in-house research project and won't be released, Guzdial notes that the Google DeepMind team says it could one day be turned into a game-making tool--something he's working on too. "I'm definitely interested to see what they build," he says.

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.

Not to be outdone by Meta's Make-A-Video, Google today detailed its work on Imagen Video, an AI system that can generate video clips given a text prompt (e.g., "a teddy bear washing dishes"). While the results aren't perfect -- the looping clips the system generates tend to have artifacts and noise -- Google claims that Imagen Video is a step toward a system with a "high degree of controllability" and world knowledge, including the ability to generate footage in a range of artistic styles. As my colleague Devin Coldewey noted in his piece about Make-A-Video, text-to-video systems aren't new. Earlier this year, a group of researchers from Tsinghua University and the Beijing Academy of Artificial Intelligence released CogVideo, which can translate text into reasonably-high-fidelity short clips. But Imagen Video appears to be a significant leap over the previous state-of-the-art, showing an aptitude for animating captions that existing systems would have trouble understanding.

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.

The Allen Institute for AI (AI2), the division within the nonprofit Allen Institute focused on machine learning research, today published its work on an AI system, called Unified-IO, that it claims is among the first to perform a "large and diverse" set of AI tasks. Unified-IO can process and create images, text and other structured data, a feat that the research team behind it says is a step toward building capable, unified general-purpose AI systems. "We are interested in building task-agnostic [AI systems], which can enable practitioners to train [machine learning] models for new tasks with little to no knowledge of the underlying machinery," Jaisen Lu, a research scientist at AI2 who worked on Unified-IO, told TechCrunch via email. "Such unified architectures alleviate the need for task-specific parameters and system modifications, can be jointly trained to perform a large variety of tasks and can share knowledge across tasks to boost performance." AI2's early efforts in building unified AI systems led to GPV-1 and GPV-2, two general-purpose, "vision-language" systems that supported a handful of workloads including captioning images and answering questions.

In this paper we propose the application of techniques from the field of creativity research to machine learned models within the domain of games. This application allows for the creation of new, distinct models without additional training data. The techniques in question are combinatorial creativity techniques, defined as techniques that combine two sets of input to create novel output sets. We present a survey of prior work in this area and a case study applying some of these techniques to pre-trained machine learned models of game level design.

Automatic analysis of game levels can provide as- sistance to game designers and procedural content generation. We introduce a static-dynamic scale to categorize level analysis strategies, which captures the extent that the analysis depends on player simulation. Due to its ability to automatically learn intermediate representations for the task, a convolutional neural network (CNN) provides a general tool for both types of analysis. In this paper, we explore the use of CNN to analyze 1,437 Infinite Mario levels. We further propose a deep reinforcement learning technique for dynamic analysis, which allows the simulated player to pay a penalty to reduce error in its control. We empirically demonstrate the effectiveness of our techniques and complementarity of dynamic and static analysis.

We present an unsupervised process to generate full video game levels from a model trained on gameplay video. The model represents probabilistic relationships between shapes properties, and relates the relationships to stylistic variance within a domain. We utilize the classic platformer game Super Mario Bros. to evaluate this process due to its highly-regarded level design. We evaluate the output in comparison to other data-driven level generation techniques via a user study and demonstrate its ability to produce novel output more stylistically similar to exemplar input.