Describing skills in natural language has the potential to provide an accessible way to inject human knowledge about decision-making into an AI system. We present MaestroMotif, a method for AI-assisted skill design, which yields high-performing and adaptable agents. MaestroMotif leverages the capabilities of Large Language Models (LLMs) to effectively create and reuse skills. It first uses an LLM's feedback to automatically design rewards corresponding to each skill, starting from their natural language description. Then, it employs an LLM's code generation abilities, together with reinforcement learning, for training the skills and combining them to implement complex behaviors specified in language. We evaluate MaestroMotif using a suite of complex tasks in the NetHack Learning Environment (NLE), demonstrating that it surpasses existing approaches in both performance and usability.

翻译：使用自然语言描述技能，有望为将人类决策知识注入人工智能系统提供一种便捷途径。我们提出了MaestroMotif，一种人工智能辅助的技能设计方法，能够生成高性能且适应性强的智能体。MaestroMotif利用大型语言模型（LLMs）的能力来高效创建和复用技能。该方法首先基于技能的自然语言描述，利用LLM的反馈自动设计对应每个技能的奖励函数。随后，它结合LLM的代码生成能力与强化学习技术，对技能进行训练并将其组合，以实现语言指定的复杂行为。我们在NetHack学习环境（NLE）的一系列复杂任务上评估了MaestroMotif，结果表明其在性能和易用性方面均超越了现有方法。