arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.09013cs.AIcs.LG
收藏

通过生成式人工智能进行过程内容生成

Procedural Content Generation via Generative Artificial Intelligence

Duke University(杜克大学);Tohoku University(东北大学)

Xinyu Mao, Wanli Yu, Yuya Okawara, Xueying Zhan, Kazunori D. Yamada, Michael R. Zielewski

AI总结:

研究如何将生成式人工智能用于过程内容生成,回顾其在创建多种内容上的应用,指出构建高性能模型面临训练数据有限问题,强调克服此问题对推动PCG研究的重要性,并关注相关应对研究。

摘要:

过去曾尝试在过程内容生成(PCG)中运用机器学习。在本综述论文中,我们探究了在2010年代中期兴趣大幅增长的生成式人工智能如何用于PCG。我们回顾了生成式人工智能在创建各类内容(包括地形、物品甚至故事情节)方面的应用。虽然生成式人工智能对PCG有效,但面临的一个重大问题是构建高性能生成式人工智能需要大量训练数据。由于内容通常高度定制,特定领域训练数据稀缺,直接应用生成式人工智能模型可能效果不佳。为推动PCG研究进一步发展,必须克服与有限训练数据相关的问题。因此,我们也特别关注应对有限训练数据带来挑战的研究。

英文摘要:

The attempt to utilize machine learning in procedural content generation (PCG) has been made in the past. In this survey paper, we investigate how generative artificial intelligence (AI), which saw a significant increase in interest in the mid-2010s, is being used for PCG. We review applications of generative AI for the creation of various types of content, including terrains, items, and even storylines. While generative AI is effective for PCG, building high-performance models requires not only handling customized content and ensuring quality and diversity, but also securing sufficient training data. For PCG research to advance further, addressing these challenges is essential. Thus, we also give special consideration to research that explores innovative generation techniques, model architectures, and approaches suited for limited-data scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑