{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T03:08:30Z","timestamp":1776913710079,"version":"3.51.2"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["92370123"],"award-info":[{"award-number":["92370123"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62103334"],"award-info":[{"award-number":["62103334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62273280"],"award-info":[{"award-number":["62273280"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Major Project of Basic and Applied Basic Research","award":["2023B0303000016"],"award-info":[{"award-number":["2023B0303000016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2024.3451296","type":"journal-article","created":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T18:44:18Z","timestamp":1725475458000},"page":"6643-6652","source":"Crossref","is-referenced-by-count":11,"title":["Efficient Reinforcement Learning Method for Multi-Phase Robot Manipulation Skill Acquisition via Human Knowledge, Model-Based, and Model-Free Methods"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-4908","authenticated-orcid":false,"given":"Xing","family":"Liu","sequence":"first","affiliation":[{"name":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Liu","sequence":"additional","affiliation":[{"name":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4184-0903","authenticated-orcid":false,"given":"Gaozhao","family":"Wang","sequence":"additional","affiliation":[{"name":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9427-4066","authenticated-orcid":false,"given":"Zhengxiong","family":"Liu","sequence":"additional","affiliation":[{"name":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5132-9602","authenticated-orcid":false,"given":"Panfeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.107718"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3059912"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3139096"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.035"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.039"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2012.2210294"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103568"},{"key":"ref8","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Deisenroth"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1561\/2300000021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2623817"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s41315-020-00138-z"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-022-10034-z"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103711"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10085-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3288037"},{"key":"ref18","first-page":"757","article-title":"Efficient hierarchical robot motion planning under uncertainty and hybrid dynamics","volume-title":"Proc. Conf. Robot. Learn.","author":"Jain"},{"key":"ref19","article-title":"Sub-policy adaptation for hierarchical reinforcement learning","author":"Li","year":"2019","journal-title":"arXiv:1906.05862"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139389"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3038072"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/820"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2958211"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3357236.3395525"},{"key":"ref25","article-title":"Tactile active inference reinforcement learning for efficient robotic manipulation skill acquisition","author":"Liu","year":"2023","journal-title":"arXiv:2311.11287"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793542"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2791591"},{"key":"ref28","article-title":"Plan-seq-learn: Language model guided RL for solving long horizon robotics tasks","author":"Dalal","year":"2024","journal-title":"arXiv:2405.01534"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/10665750.pdf?arnumber=10665750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T05:49:00Z","timestamp":1741844940000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10665750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3451296","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}