arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.06111cs.AIcs.CL
收藏

询问知识:训练RL Agent使用语言查询外部知识

Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Microsoft Research(微软研究院);Inria(法国国家信息与自动化研究所)

Iou-Jen Liu, Xingdi Yuan, Marc-Alexandre Côté, Pierre-Yves Oudeyer, Alexander G. Schwing

摘要:

为了解决困难的任务,人类会问问题,从外部来源获取知识。相比之下,经典的强化学习代理缺乏这样的能力,往往诉诸探索行为。这是加剧了目前的环境支持查询的知识。为了研究如何教代理通过语言查询外部知识,我们首先介绍了两个新的环境:基于网格世界的Q-BabyAI和基于文本的Q-TextWorld。除了物理交互之外,代理还可以查询专门针对这些环境的外部知识源以收集信息。其次,我们提出了“询问知识”(AFK)代理,它学习生成语言命令来查询有意义的知识,帮助解决任务。AFK利用非参数存储器、指针机制和情节探索奖励来处理(1)不相关的信息,(2)大的查询语言空间,(3)进行有意义的查询的延迟奖励。大量的实验表明,AFK代理在具有挑战性的Q-BabyAI和Q-TextWorld环境中的表现优于最近的基线。

英文摘要:

To solve difficult tasks, humans ask questions to acquire knowledge from external sources. In contrast, classical reinforcement learning agents lack such an ability and often resort to exploratory behavior. This is exacerbated as few present-day environments support querying for knowledge. In order to study how agents can be taught to query external knowledge via language, we first introduce two new environments: the grid-world-based Q-BabyAI and the text-based Q-TextWorld. In addition to physical interactions, an agent can query an external knowledge source specialized for these environments to gather information. Second, we propose the "Asking for Knowledge" (AFK) agent, which learns to generate language commands to query for meaningful knowledge that helps solve the tasks. AFK leverages a non-parametric memory, a pointer mechanism and an episodic exploration bonus to tackle (1) irrelevant information, (2) a large query language space, (3) delayed reward for making meaningful queries. Extensive experiments demonstrate that the AFK agent outperforms recent baselines on the challenging Q-BabyAI and Q-TextWorld environments.

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。

↑