Text-based reinforcement learning agents have predominantly been neural network-based models with embeddings-based representation, learning uninterpretable policies that often do not generalize well to unseen games. On the other hand, neuro-symbolic methods, specifically those that leverage an intermediate formal representation, are gaining significant attention in language understanding tasks. This is because of their advantages ranging from inherent interpretability, the lesser requirement of training data, and being generalizable in scenarios with unseen data. Therefore, in this paper, we propose a modular, NEuro-Symbolic Textual Agent (NESTA) that combines a generic semantic parser with a rule induction system to learn abstract interpretable rules as policies. Our experiments on established text-based game benchmarks show that the proposed NESTA method outperforms deep reinforcement learning-based techniques by achieving better generalization to unseen test games and learning from fewer training interactions.

翻译：基于文本的强化学习Agent主要采用基于嵌入表示的神经网络模型，学习不可解释的策略，且往往难以泛化到未见过的游戏中。另一方面，神经符号方法，特别是利用中间形式表示的方法，在语言理解任务中日益受到关注。这是因为它们具有内在可解释性、训练数据需求较少以及在未见数据场景下具备泛化能力等优势。因此，本文提出一种模块化的神经符号文本Agent（NESTA），该Agent将通用语义解析器与规则归纳系统相结合，学习可解释的抽象规则作为策略。在已建立的文本游戏基准测试上的实验表明，所提出的NESTA方法通过更少的训练交互实现了更好的泛化性能，在未见测试游戏中优于基于深度强化学习的技术。