MarioGPT: Open-Ended Text2Level Generation through Large Language Models
This addresses the problem of generating intentional and open-ended content in game design, though it is incremental as it applies existing LLM techniques to a new domain.
The authors tackled the challenge of generating meaningful and controllable game levels in procedural content generation by introducing MarioGPT, a fine-tuned GPT2 model that generates tile-based Super Mario Bros levels from text prompts, enabling diverse and open-ended level creation.
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.