arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.02050cs.NEcs.AIcs.LG
收藏

RL中的推理和泛化:一个工具使用的视角

Reasoning and Generalization in RL: A Tool Use Perspective

Fomoro AI(Fomoro人工智能公司)

Sam Wenke, Dan Saunders, Mike Qiu, Jim Fleming

摘要:

学会使用工具来解决各种任务是人类与生俱来的能力,在野生动物中也观察到了这一点。然而,学习使用工具所需的基本机制是抽象的,在文献中存在广泛争议。在本文中,我们研究工具使用的背景下,强化学习,并提出了一个框架,分析泛化的工具使用行为的经典研究,陷阱管任务的启发。最近,在强化学习中衡量单个环境测试集上的泛化性能变得很常见。相反,我们提出的转移,产生多个测试集,用于测量指定类型的泛化,动物和人类工具用户所展示的能力的启发。复制我们实验的源代码可在https://github.com/fomorians/gym_tool_use上公开获得。

英文摘要:

Learning to use tools to solve a variety of tasks is an innate ability of humans and has been observed of animals in the wild. However, the underlying mechanisms that are required to learn to use tools are abstract and widely contested in the literature. In this paper, we study tool use in the context of reinforcement learning and propose a framework for analyzing generalization inspired by a classic study of tool using behavior, the trap-tube task. Recently, it has become common in reinforcement learning to measure generalization performance on a single test set of environments. We instead propose transfers that produce multiple test sets that are used to measure specified types of generalization, inspired by abilities demonstrated by animal and human tool users. The source code to reproduce our experiments is publicly available at https://github.com/fomorians/gym_tool_use.

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。

↑