Summary of Procedural Content Generation Via Generative Artificial Intelligence, by Xinyu Mao et al.
Procedural Content Generation via Generative Artificial Intelligence
by Xinyu Mao, Wanli Yu, Kazunori D Yamada, Michael R. Zielewski
First submitted to arxiv on: 12 Jul 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The survey paper investigates the application of generative artificial intelligence (AI) in procedural content generation (PCG). Generative AI saw a significant increase in interest in the mid-2010s and is being used for creating various types of content, including terrains, items, and storylines. While effective for PCG, building high-performance generative AI requires vast amounts of training data, which is scarce due to customized nature of content. To overcome this challenge, research that addresses limited training data must be conducted. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how machine learning can help create new things in games and other digital worlds. Generative AI is a type of artificial intelligence that can make lots of different things, like landscapes, objects, and even stories. But making good generative AI models takes a lot of training data, which is hard to find because people want customized content. The paper wants to help solve this problem by looking at research that can overcome the limitations of having too little training data. |
Keywords
» Artificial intelligence » Machine learning
