<ul><li>Recent research has highlighted the significance of natural language in enhancing the controllability of generative models.</li><li>IPCGRL is an instruction-based procedural content generation method via reinforcement learning, incorporating a sentence embedding model.</li><li>IPCGRL achieves up to a 21.4% improvement in controllability and a 17.2% improvement in generalizability for unseen instructions.</li><li>The proposed method extends the modality of conditional input, enabling a more flexible and expressive interaction framework for procedural content generation.</li></ul>

IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generation

Discover more