{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T10:19:27Z","timestamp":1752229167234,"version":"3.37.3"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T00:00:00Z","timestamp":1711324800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T00:00:00Z","timestamp":1711324800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62293514,62003136"],"award-info":[{"award-number":["62293514,62003136"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,3,25]]},"DOI":"10.1109\/icit58233.2024.10570082","type":"proceedings-article","created":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T17:38:50Z","timestamp":1719509930000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["A reinforcement learning based control framework for robot gear assembly with demonstration learning and force feedback"],"prefix":"10.1109","author":[{"given":"Wenjie","family":"Tang","sequence":"first","affiliation":[{"name":"College of Robotics, Hunan University,ChangSha,China"}]},{"given":"Yiming","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Robotics, Hunan University,ChangSha,China"}]},{"given":"Chao","family":"Zeng","sequence":"additional","affiliation":[{"name":"Universität Hamburg,Department of Informatics,Hamburg,Germany"}]},{"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Robotics, Hunan University,ChangSha,China"}]},{"given":"Hang","family":"Zhong","sequence":"additional","affiliation":[{"name":"College of Robotics, Hunan University,ChangSha,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/robotics7020017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574718001145"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793506"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"issue":"1","key":"ref5","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793506"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfoodeng.2022.111117"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2959445"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref12","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"journal-title":"python module for physics simulation for games, robotics and machine learning","year":"2016","author":"Coumans","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981802"},{"issue":"1","key":"ref17","first-page":"1395","article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms","volume":"22","author":"Kroemer","year":"2021","journal-title":"The Journal of Machine Learning Research"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s41315-019-00103-5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3237734"},{"key":"ref20","article-title":"Deep exploration via bootstrapped dqn","volume":"29","author":"Osband","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Prox-imal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref24","first-page":"32","article-title":"Learning from demonstrations for real world reinforcement learning","author":"Sendonaris","year":"2017","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE International Conference on Industrial Technology (ICIT)","start":{"date-parts":[[2024,3,25]]},"location":"Bristol, United Kingdom","end":{"date-parts":[[2024,3,27]]}},"container-title":["2024 IEEE International Conference on Industrial Technology (ICIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10540646\/10540608\/10570082.pdf?arnumber=10570082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T17:41:44Z","timestamp":1721842904000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10570082\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,25]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icit58233.2024.10570082","relation":{},"subject":[],"published":{"date-parts":[[2024,3,25]]}}}