TL;DR本文研究了在文本游戏中使用基于视觉数据集得到的常识推理有助于提高游戏 AI 效率的优势,对比了空间关系的统计信息并在常识推理任务中进行验证实验,结果表明该方法优于现有最先进的方法。
Abstract
Text-based games are becoming commonly used in reinforcement learning as
real-world simulation environments. They are usually imperfect information
games, and their interactions are only in the textual modality. To challenge
these games, it is effective to complement the missing inform