Mathieu Tuli, Andrew C. Li, Pashootan Vaezipoor, Toryn Q. Klassen, Scott Sanner...
TL;DR研究文本游戏在强化学习环境下的指令正确率,设计使用 Linear Temporal Logic 结构化语言支持时间上下文语义的指令,通过文字游戏的实验验证该结构化语言指令的有效性和优越性。
Abstract
text-based games present a unique class of sequential decision making problem in which agents interact with a partially observable, simulated environment via actions and observations conveyed through natural language. Such observations typically include instructions that, in a