Procedural Content Generation (PCG) algorithms provide a technique to generate complex and diverse environments in an automated way. However, while generating content with PCG methods is often straightforward, generating meaningful content that reflects specific intentions and constraints remains challenging. Furthermore, many PCG algorithms lack the ability to generate content in an open-ended manner. Recently, Large Language Models (LLMs) have shown to be incredibly effective in many diverse domains. These trained LLMs can be fine-tuned, re-using information and accelerating training for new tasks. In this work, we introduce MarioGPT, a fine-tuned GPT2 model trained to generate tile-based game levels, in our case Super Mario Bros levels. We show that MarioGPT can not only generate diverse levels, but can be text-prompted for controllable level generation, addressing one of the key challenges of current PCG techniques. As far as we know, MarioGPT is the first text-to-level model. We also combine MarioGPT with novelty search, enabling it to generate diverse levels with varying play-style dynamics (i.e. player paths). This combination allows for the open-ended generation of an increasingly diverse range of content.

翻译：程序化内容生成（PCG）算法提供了一种自动生成复杂多样环境的技术。然而，尽管使用PCG方法生成内容通常较为直接，但生成反映特定意图与约束的有意义内容仍具挑战性。此外，许多PCG算法缺乏以开放式方式生成内容的能力。近年来，大型语言模型（LLM）已在众多不同领域展现出惊人的有效性。这些经过训练的LLM可被微调，从而重用信息并加速新任务的训练。本研究提出了MarioGPT——一个经过微调的GPT2模型，专门用于生成基于图块的游戏关卡（本例中为《超级马里奥兄弟》关卡）。我们证明，MarioGPT不仅能生成多样化关卡，还可通过文本提示实现可控的关卡生成，从而解决了当前PCG技术的关键挑战之一。据我们所知，MarioGPT是首个文本到关卡模型。我们还将MarioGPT与新颖性搜索相结合，使其能够生成具有不同玩法动态（即玩家路径）的多样化关卡。这种组合实现了日益多样化内容的开放式生成。