Procedural Level Generation in Educational Games From Natural Language Instruction

In the evolving field of mixed-initiative game design, where procedural content generation plays a pivotal role, establishing a comprehensive approach that empowers nontechnical designers to actively shape content generation is essential. Recent developments in large language models (LLMs) significantly alter the landscape of automated text-based content generation. These models offer a significant advantage in mixed-initiative procedural level generation by providing designers with intuitive, natural language (NL) interfaces. The framework presented in this article interprets NL inputs, detailing level design constraints and optimization goals, to aid in the cooperative development of game levels for a strategy game aimed at environmental sustainability education. It enables designers to articulate their vision concerning the problem domain, goal metrics, and desired difficulty level through a textual description. By utilizing LLMs, the framework extracts semantic constraints and optimization objectives, which are then used to generate candidate game levels. The efficacy of these levels is assessed by game-playing agents trained through advanced deep reinforcement learning methods, ensuring alignment with the designer's original specifications. We further evaluate our framework with both experts and nonexperts in designing levels for our strategy game. Their detailed responses confirm that our framework effectively translates NL descriptions into playable game levels, accurately capturing the designers' intended objectives.