Lifelong Learning and Personalization in Long-Term Human-Robot Interaction (LEAP-HRI): Open-World Learning

Author:

Irfan Bahar1ORCID,Staffa Mariacarla2ORCID,Bobu Andreea3ORCID,Churamani Nikhil4ORCID

Affiliation:

1. Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden

2. University of Naples Parthenope, Naples, Italy

3. Boston Dynamics AI Institute, Cambridge, MA, USA

4. University of Cambridge, Cambridge, United Kingdom

Funder

Google

KTH Digital Futures

Italian Ministry of University and Research

Next Generation EU

Publisher

ACM

Reference19 articles.

1. David Abel, Andre Barreto, Benjamin Van Roy, Doina Precup, Hado van Hasselt, and Satinder Singh. 2023. A Definition of Continual Reinforcement Learning. In Thirty-seventh Conference on Neural Information Processing Systems.

2. Abhijit Bendale and Terrance Boult. 2015. Towards Open World Recognition. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE.

3. Diana Borsa, Thore Graepel, and John Shawe-Taylor. 2016. Learning shared representations in multi-task reinforcement learning. arXiv preprint:1603.02041 (2016).

4. Zhiyuan Chen and Bing Liu. 2018. Lifelong Machine Learning. Springer International Publishing, Cham.

5. Continual Learning for Affective Robotics: Why, What and How?

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3