arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.04040cs.AI
收藏

强化学习中自然语言标记任务的快速自适应

Fast Task-Adaptation for Tasks Labeled Using Natural Language in Reinforcement Learning

University of Antwerp - imec(安特卫普大学-imec)

Matthias Hutsebaut-Buysse, Kevin Mets, Steven Latré

摘要:

在其生命周期中,强化学习代理通常被赋予不同的任务。如何有效地适应以前学习的控制策略从一个任务到另一个任务,仍然是一个开放的研究问题。在本文中,我们研究如何制定自然语言的指令可以使更快,更有效的任务适应。这可以作为发展语言指导技能的基础,这些技能可以在终身学习环境中使用。我们的方法是能够评估,给定一组发达的基础控制政策,该政策将最好地适应一个新的看不见的任务。

英文摘要:

Over its lifetime, a reinforcement learning agent is often tasked with different tasks. How to efficiently adapt a previously learned control policy from one task to another, remains an open research question. In this paper, we investigate how instructions formulated in natural language can enable faster and more effective task adaptation. This can serve as the basis for developing language instructed skills, which can be used in a lifelong learning setting. Our method is capable of assessing, given a set of developed base control policies, which policy will adapt best to a new unseen task.

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。

↑