Procedural Content Generation via Machine Learning (PCGML) faces a significant hurdle that sets it apart from other fields, such as image or text generation, which is limited annotated data. Many existing methods for procedural level generation via machine learning require a secondary representation besides level images. However, the current methods for obtaining such representations are laborious and time-consuming, which contributes to this problem. In this work, we aim to address this problem by utilizing gameplay videos of two human-annotated games to develop a novel multi-tail framework that learns to perform simultaneous level translation and generation. The translation tail of our framework can convert gameplay video frames to an equivalent secondary representation, while its generation tail can produce novel level segments. Evaluation results and comparisons between our framework and baselines suggest that combining the level generation and translation tasks can lead to an overall improved performance regarding both tasks. This represents a possible solution to limited annotated level data, and we demonstrate the potential for future versions to generalize to unseen games.

翻译：通过机器学习进行程序化内容生成面临一个显著障碍——与图像或文本生成等领域不同，其可用标注数据极为有限。现有基于机器学习的程序化关卡生成方法大多需要除关卡图像之外的辅助表征，但当前获取此类表征的方法耗时费力，进一步加剧了数据匮乏问题。本研究旨在利用两个人工标注游戏的游戏视频，开发一种新颖的多尾框架，实现关卡翻译与生成的同步学习。该框架的翻译分支可将游戏视频帧转换为等效的辅助表征，而生成分支则可生成全新的关卡片段。评估结果及与基线模型的对比表明，将关卡生成与翻译任务相结合可全面提升两项任务的性能。这为有限标注关卡数据问题提供了可行解决方案，并展现了未来版本向未见游戏泛化的潜力。