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 2106.00133cs.AI
收藏

AppBuddy:通过强化学习学习在移动应用中完成任务

AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning

University of Toronto(多伦多大学);Samsung AI Center(三星人工智能中心)

Maayan Shvo, Zhiming Hu, Rodrigo Toro Icarte, Iqbal Mohomed, Allan Jepson, Sheila A. McIlraith

摘要:

人类,甚至是小孩子,很快就学会了如何在移动设备上使用应用程序。学习使用一个新的应用程序通常是通过试错来实现的,通过从过去的经验中转移知识来加速。制造一款更智能的智能手机--一款可以学习如何使用移动应用程序完成任务的智能手机--的前景是诱人的。在本文中,我们将探索强化学习(RL)的使用,以推进这一愿望。我们引入了一个基于RL的框架,用于学习在移动应用程序中完成任务。RL代理被提供有从屏幕上元素的底层表示导出的状态,以及基于任务中所取得的进展的奖励。座席可以通过点击或键入来与屏幕元素交互。我们在许多移动应用程序上的实验结果表明,RL代理可以学习完成多步任务,并在不同的应用程序中实现适度的泛化。更一般地说,我们开发了一个平台,解决了几个工程挑战,使一个有效的RL培训环境。我们的AppBuddy平台与OpenAI Gym兼容,包括一套移动应用程序和基准任务,支持移动应用程序环境中的多种RL研究。

英文摘要:

Human beings, even small children, quickly become adept at figuring out how to use applications on their mobile devices. Learning to use a new app is often achieved via trial-and-error, accelerated by transfer of knowledge from past experiences with like apps. The prospect of building a smarter smartphone - one that can learn how to achieve tasks using mobile apps - is tantalizing. In this paper we explore the use of Reinforcement Learning (RL) with the goal of advancing this aspiration. We introduce an RL-based framework for learning to accomplish tasks in mobile apps. RL agents are provided with states derived from the underlying representation of on-screen elements, and rewards that are based on progress made in the task. Agents can interact with screen elements by tapping or typing. Our experimental results, over a number of mobile apps, show that RL agents can learn to accomplish multi-step tasks, as well as achieve modest generalization across different apps. More generally, we develop a platform which addresses several engineering challenges to enable an effective RL training environment. Our AppBuddy platform is compatible with OpenAI Gym and includes a suite of mobile apps and benchmark tasks that supports a diversity of RL research in the mobile app setting.

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。

↑