{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T07:19:04Z","timestamp":1772090344997,"version":"3.50.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":["62273341"],"award-info":[{"award-number":["62273341"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Municipal Natural Science Foundation","award":["4212044"],"award-info":[{"award-number":["4212044"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tii.2023.3240936","type":"journal-article","created":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T19:43:32Z","timestamp":1675107812000},"page":"10254-10264","source":"Crossref","is-referenced-by-count":27,"title":["Hierarchical Policy Learning With Demonstration Learning for Robotic Multiple Peg-in-Hole Assembly Tasks"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2575-1447","authenticated-orcid":false,"given":"Shaohua","family":"Yan","sequence":"first","affiliation":[{"name":"Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7221-1654","authenticated-orcid":false,"given":"De","family":"Xu","sequence":"additional","affiliation":[{"name":"Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5834-5181","authenticated-orcid":false,"given":"Xian","family":"Tao","sequence":"additional","affiliation":[{"name":"Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICONC345789.2020.9117551"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1108\/IR-07-2016-0186"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ETFA45728.2021.9613614"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/UR49135.2020.9144946"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3144282"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/APCCAS.1998.743873"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197327"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3135552"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3043226"},{"key":"ref17","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref16","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref18","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn Mach Learn Res"},{"key":"ref24","first-page":"5055","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref23","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2868859"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.3024725"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2928212"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3038072"},{"key":"ref21","first-page":"3540","article-title":"FeUdal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561619"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341678"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3020065"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594370"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2332543"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2897731"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2174\/092986608783489490"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636179"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2019.2921224"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2838069"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424\/10214691\/10032219.pdf?arnumber=10032219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T18:33:47Z","timestamp":1693852427000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10032219\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":30,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tii.2023.3240936","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}