Moonshine: Distilling Game Content Generators into Steerable Generative Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910809475514368 |
|---|---|
| author | Nie, Yuhe Middleton, Michael Merino, Tim Kanagaraja, Nidhushan Kumar, Ashutosh Zhuang, Zhan Togelius, Julian |
| author_facet | Nie, Yuhe Middleton, Michael Merino, Tim Kanagaraja, Nidhushan Kumar, Ashutosh Zhuang, Zhan Togelius, Julian |
| contents | Procedural Content Generation via Machine Learning (PCGML) has enhanced game content creation, yet challenges in controllability and limited training data persist. This study addresses these issues by distilling a constructive PCG algorithm into a controllable PCGML model. We first generate a large amount of content with a constructive algorithm and label it using a Large Language Model (LLM). We use these synthetic labels to condition two PCGML models for content-specific generation, a diffusion model and the five-dollar model. This neural network distillation process ensures that the generation aligns with the original algorithm while introducing controllability through plain text. We define this text-conditioned PCGML as a Text-to-game-Map (T2M) task, offering an alternative to prevalent text-to-image multi-modal tasks. We compare our distilled models with the baseline constructive algorithm. Our analysis of the variety, accuracy, and quality of our generation demonstrates the efficacy of distilling constructive methods into controllable text-conditioned PCGML models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_09594 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Moonshine: Distilling Game Content Generators into Steerable Generative Models Nie, Yuhe Middleton, Michael Merino, Tim Kanagaraja, Nidhushan Kumar, Ashutosh Zhuang, Zhan Togelius, Julian Artificial Intelligence I.2.1 Procedural Content Generation via Machine Learning (PCGML) has enhanced game content creation, yet challenges in controllability and limited training data persist. This study addresses these issues by distilling a constructive PCG algorithm into a controllable PCGML model. We first generate a large amount of content with a constructive algorithm and label it using a Large Language Model (LLM). We use these synthetic labels to condition two PCGML models for content-specific generation, a diffusion model and the five-dollar model. This neural network distillation process ensures that the generation aligns with the original algorithm while introducing controllability through plain text. We define this text-conditioned PCGML as a Text-to-game-Map (T2M) task, offering an alternative to prevalent text-to-image multi-modal tasks. We compare our distilled models with the baseline constructive algorithm. Our analysis of the variety, accuracy, and quality of our generation demonstrates the efficacy of distilling constructive methods into controllable text-conditioned PCGML models. |
| title | Moonshine: Distilling Game Content Generators into Steerable Generative Models |
| topic | Artificial Intelligence I.2.1 |
| url | https://arxiv.org/abs/2408.09594 |