IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generation
This work addresses the limited controllability of procedural content generation in games using language instructions, representing an incremental advance in domain-specific applications.
The paper tackles the problem of using natural language instructions to control procedural content generation in reinforcement learning, achieving a 21.4% improvement in controllability and a 17.2% improvement in generalizability for unseen instructions.
Recent research has highlighted the significance of natural language in enhancing the controllability of generative models. While various efforts have been made to leverage natural language for content generation, research on deep reinforcement learning (DRL) agents utilizing text-based instructions for procedural content generation remains limited. In this paper, we propose IPCGRL, an instruction-based procedural content generation method via reinforcement learning, which incorporates a sentence embedding model. IPCGRL fine-tunes task-specific embedding representations to effectively compress game-level conditions. We evaluate IPCGRL in a two-dimensional level generation task and compare its performance with a general-purpose embedding method. The results indicate that IPCGRL achieves up to a 21.4% improvement in controllability and a 17.2% improvement in generalizability for unseen instructions. Furthermore, the proposed method extends the modality of conditional input, enabling a more flexible and expressive interaction framework for procedural content generation.