arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.04591cs.LGcs.AIcs.CL
收藏

学习在基于文本的游戏中遵循指令

Learning to Follow Instructions in Text-Based Games

University of Toronto(多伦多大学);Vector Institute for Artificial Intelligence(矢量人工智能研究所);Schwartz Reisman Institute for Technology and Society(施瓦茨·赖斯曼技术与社会研究所)

Mathieu Tuli, Andrew C. Li, Pashootan Vaezipoor, Toryn Q. Klassen, Scott Sanner, Sheila A. McIlraith

摘要:

基于文本的游戏提出了一类独特的顺序决策问题,其中代理人通过自然语言传达的动作和观察与部分可观察的模拟环境进行交互。此类观察通常包括在强化学习(RL)设置中可以直接或间接引导玩家完成值得奖励的任务的指令。在这项工作中,我们研究的RL代理遵循这样的指示的能力。我们进行的实验表明,国家的最先进的基于文本的游戏代理的性能在很大程度上不受存在或不存在这样的指令,这些代理通常无法执行任务完成。为了进一步研究和解决指令遵循的任务,我们配备了RL代理的内部结构化表示的自然语言指令的形式线性时序逻辑(LTL),一种形式语言,越来越多地用于时间扩展的奖励规范在RL。我们的框架既支持和突出的好处,理解的时间语义的指令,并在衡量实现这样一个时间上的扩展行为的进展。在TextWorld中使用500多个游戏的实验证明了我们方法的优越性能。

英文摘要:

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 reinforcement learning (RL) setting, can directly or indirectly guide a player towards completing reward-worthy tasks. In this work, we study the ability of RL agents to follow such instructions. We conduct experiments that show that the performance of state-of-the-art text-based game agents is largely unaffected by the presence or absence of such instructions, and that these agents are typically unable to execute tasks to completion. To further study and address the task of instruction following, we equip RL agents with an internal structured representation of natural language instructions in the form of Linear Temporal Logic (LTL), a formal language that is increasingly used for temporally extended reward specification in RL. Our framework both supports and highlights the benefit of understanding the temporal semantics of instructions and in measuring progress towards achievement of such a temporally extended behaviour. Experiments with 500+ games in TextWorld demonstrate the superior performance of our approach.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑