{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:12:49Z","timestamp":1783699969123,"version":"3.55.0"},"reference-count":42,"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":"Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373285"],"award-info":[{"award-number":["62373285"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai 2021 Science and Technology Innovation Action Plan with the Special Project of Biomedical Science and Technology Support","award":["21S31902800"],"award-info":[{"award-number":["21S31902800"]}]},{"name":"Key Pre-Research Project of the 14th-Five-Year-Plan on Common Technology"},{"name":"National Major Talent Plan Project","award":["2022-XXXX-XXX-079"],"award-info":[{"award-number":["2022-XXXX-XXX-079"]}]},{"name":"Fundamental Research Project","award":["XXXX2022YYYC133"],"award-info":[{"award-number":["XXXX2022YYYC133"]}]},{"name":"Shanghai Industrial Collaborative Innovation Project","award":["HCXBCY-2022-051"],"award-info":[{"award-number":["HCXBCY-2022-051"]}]},{"name":"Project of the Space Structure and Mechanism Technology Laboratory of China Aerospace Science and Technology Group Company Ltd.","award":["YY-F805202210015"],"award-info":[{"award-number":["YY-F805202210015"]}]},{"name":"Project of the National Laboratory of Space Intelligent Control","award":["HTKJ2023KL502016"],"award-info":[{"award-number":["HTKJ2023KL502016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2024.3352584","type":"journal-article","created":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T18:40:22Z","timestamp":1705603222000},"page":"466-479","source":"Crossref","is-referenced-by-count":52,"title":["A Task-Adaptive Deep Reinforcement Learning Framework for Dual-Arm Robot Manipulation"],"prefix":"10.1109","volume":"22","author":[{"given":"Yuanzhe","family":"Cui","sequence":"first","affiliation":[{"name":"Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8591-5581","authenticated-orcid":false,"given":"Zhipeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lou","family":"Zhong","sequence":"additional","affiliation":[{"name":"Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengjie","family":"Xu","sequence":"additional","affiliation":[{"name":"Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichao","family":"Shen","sequence":"additional","affiliation":[{"name":"Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5541-4660","authenticated-orcid":false,"given":"Qirong","family":"Tang","sequence":"additional","affiliation":[{"name":"Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2958876"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981909"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2012.2205651"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/70.976030"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364902021009119"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2708134"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574714001234"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3130433"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3175260"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919868530"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574721000941"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref15","first-page":"7740","article-title":"Retrieval-augmented reinforcement learning","volume-title":"Proc. Mach. Learn. Res. (ICML)","author":"Goyal"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8665049"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.06.007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2013.7030010"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106281"},{"key":"ref20","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2019","journal-title":"arXiv:1509.02971"},{"key":"ref21","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/027836498700600304"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TRA.2004.824941"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cirp.2011.03.017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487162"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aat6385"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2020.106446"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2022.108098"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3056903"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/s20205911"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2022.107980"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3295991"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2023.3262461"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/mi13040564"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s41315-019-00103-5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tmech.2023.3295249"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2019.1636715"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2148230"},{"key":"ref40","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Mach. Learn. Res. (ICML)","author":"Haarnoja"},{"key":"ref41","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Mach. Learn. Res. (ICML)","author":"Fujimoto"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8856\/10839176\/10409120.pdf?arnumber=10409120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T19:15:12Z","timestamp":1737400512000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10409120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3352584","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}