A survey of demonstration learning

IF 4.3 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Robotics and Autonomous Systems Pub Date : 2024-09-13 DOI:10.1016/j.robot.2024.104812
André Correia, Luís A. Alexandre
{"title":"A survey of demonstration learning","authors":"André Correia,&nbsp;Luís A. Alexandre","doi":"10.1016/j.robot.2024.104812","DOIUrl":null,"url":null,"abstract":"<div><p>With the fast improvement of machine learning, reinforcement learning (RL) has been used to automate human tasks in different areas. However, training such agents is difficult and restricted to expert users. Moreover, it is mostly limited to simulation environments due to the high cost and safety concerns of interactions in the real-world. Demonstration Learning is a paradigm in which an agent learns to perform a task by imitating the behavior of an expert shown in demonstrations. Learning from demonstration accelerates the learning process by improving sample efficiency, while also reducing the effort of the programmer. Because the task is learned without interacting with the environment, demonstration learning allows the automation of a wide range of real-world applications such as robotics and healthcare. This paper provides a survey of demonstration learning, where we formally introduce the demonstration problem along with its main challenges and provide a comprehensive overview of the process of learning from demonstrations from the creation of the demonstration data set, to learning methods from demonstrations, and optimization by combining demonstration learning with different machine learning methods. We also review the existing benchmarks and identify their strengths and limitations. Additionally, we discuss the advantages and disadvantages of the paradigm as well as its main applications. Lastly, we discuss the open problems and future research directions of the field.</p></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"182 ","pages":"Article 104812"},"PeriodicalIF":4.3000,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0921889024001969/pdfft?md5=ca55398684a5261baba6c83e357cba9b&pid=1-s2.0-S0921889024001969-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Robotics and Autonomous Systems","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0921889024001969","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

With the fast improvement of machine learning, reinforcement learning (RL) has been used to automate human tasks in different areas. However, training such agents is difficult and restricted to expert users. Moreover, it is mostly limited to simulation environments due to the high cost and safety concerns of interactions in the real-world. Demonstration Learning is a paradigm in which an agent learns to perform a task by imitating the behavior of an expert shown in demonstrations. Learning from demonstration accelerates the learning process by improving sample efficiency, while also reducing the effort of the programmer. Because the task is learned without interacting with the environment, demonstration learning allows the automation of a wide range of real-world applications such as robotics and healthcare. This paper provides a survey of demonstration learning, where we formally introduce the demonstration problem along with its main challenges and provide a comprehensive overview of the process of learning from demonstrations from the creation of the demonstration data set, to learning methods from demonstrations, and optimization by combining demonstration learning with different machine learning methods. We also review the existing benchmarks and identify their strengths and limitations. Additionally, we discuss the advantages and disadvantages of the paradigm as well as its main applications. Lastly, we discuss the open problems and future research directions of the field.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
示范学习调查
随着机器学习的快速发展,强化学习(RL)已被用于在不同领域实现人类任务的自动化。然而,训练此类代理非常困难,而且仅限于专家用户。此外,由于在现实世界中进行交互的成本高昂且存在安全隐患,这种方法大多局限于模拟环境。演示学习(Demonstration Learning)是一种代理通过模仿演示中专家的行为来学习执行任务的范例。通过示范学习可以提高样本效率,加快学习进程,同时还能减少程序员的工作量。由于学习任务时无需与环境互动,因此示范学习可使机器人和医疗保健等广泛的现实世界应用实现自动化。本文对演示学习进行了研究,正式介绍了演示问题及其主要挑战,并全面概述了从演示数据集的创建到演示学习方法,以及通过将演示学习与不同的机器学习方法相结合进行优化的演示学习过程。我们还回顾了现有的基准,并指出了它们的优势和局限性。此外,我们还讨论了该范例的优缺点及其主要应用。最后,我们讨论了该领域的未决问题和未来研究方向。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Robotics and Autonomous Systems
Robotics and Autonomous Systems 工程技术-机器人学
CiteScore
9.00
自引率
7.00%
发文量
164
审稿时长
4.5 months
期刊介绍: Robotics and Autonomous Systems will carry articles describing fundamental developments in the field of robotics, with special emphasis on autonomous systems. An important goal of this journal is to extend the state of the art in both symbolic and sensory based robot control and learning in the context of autonomous systems. Robotics and Autonomous Systems will carry articles on the theoretical, computational and experimental aspects of autonomous systems, or modules of such systems.
期刊最新文献
Editorial Board A sensorless approach for cable failure detection and identification in cable-driven parallel robots Learning latent causal factors from the intricate sensor feedback of contact-rich robotic assembly tasks GPS-free autonomous navigation in cluttered tree rows with deep semantic segmentation Robust trajectory tracking for omnidirectional robots by means of anti-peaking linear active disturbance rejection
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1