Procedural Content Generation (PCG) is 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. Here, we introduce MarioGPT, a fine-tuned GPT2 model trained to generate tile-based game levels, in our case Super Mario Bros levels. 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 and combined with novelty search it enables the generation of diverse levels with varying play-style dynamics (i.e. player paths) and the open-ended discovery of an increasingly diverse range of content. Code available at https://github.com/shyamsn97/mario-gpt.

翻译：程序化内容生成（PCG）是一种自动化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，但生成能够反映特定意图与约束条件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（LLMs）在众多不同领域展现出惊人的有效性。这些经过训练的LLM可通过微调实现信息复用并加速新任务的训练。本文提出MarioGPT——一种基于微调GPT2模型构建的瓦片式游戏关卡（以《超级马里奥兄弟》关卡为例）生成器。MarioGPT不仅能生成多样化的关卡，还可通过文本提示进行可控化关卡生成，从而解决当前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，结合新颖性搜索技术，它能生成具有不同玩法动态（即玩家路径）的多样化关卡，并实现日益多样化的开放式内容发现。代码开源地址：https://github.com/shyamsn97/mario-gpt。