{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T21:54:01Z","timestamp":1785275641210,"version":"3.55.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["52571392"],"award-info":[{"award-number":["52571392"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3691390","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T19:43:29Z","timestamp":1778269409000},"page":"9695-9708","source":"Crossref","is-referenced-by-count":1,"title":["Linear Attention-Driven DRL With Sparse Expert Fusion: A Dynamic Optimization Algorithm of Underwater Manipulator for Long Horizon Tasks"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0634-6734","authenticated-orcid":false,"given":"Yufeng","family":"Li","sequence":"first","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1181-4531","authenticated-orcid":false,"given":"Jian","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1562-1443","authenticated-orcid":false,"given":"Yimin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3345463"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3484167"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2024.106773"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128759"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/USYS62456.2024.11116601"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3431830"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3063669"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3379048"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2944637"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3070505"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3376565"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2024.3357842"},{"key":"ref13","article-title":"Language-guided long-horizon manipulation with LLM-based planning and visual perception","author":"Zhou","year":"2025","journal-title":"arXiv:2509.02324"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3288037"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2024.3454534"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3416796"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.003"},{"key":"ref18","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume-title":"Proc. Int. Conf. Neural Inf. Process.","author":"Yu"},{"key":"ref19","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref20","first-page":"4895","article-title":"Multi-task hierarchical adversarial inverse reinforcement learning","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","author":"Chen"},{"key":"ref21","article-title":"Hierarchical reinforcement learning for efficient exploration and transfer","author":"Steccanella","year":"2020","journal-title":"arXiv:2011.06335"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3296765"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812140"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3368231"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3127574"},{"key":"ref26","first-page":"1","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Fu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061397"},{"key":"ref28","first-page":"14656","article-title":"What matters for adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Orsini"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3236882"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3308061"},{"key":"ref31","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","author":"Gupta","year":"2019","journal-title":"arXiv:1910.11956"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3140817"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3391007"},{"key":"ref34","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Haarnoja"},{"key":"ref35","first-page":"2012","article-title":"DAC: The double actor-critic architecture for learning options","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref36","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Yu"},{"key":"ref37","first-page":"2095","article-title":"Residual skill policies: Learning an adaptable skill-based action space for reinforcement learning for robotics","volume-title":"Proc. Conf. Robot. Learn","author":"Rana"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2025.3567653"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2024.118155"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3298195"},{"key":"ref41","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3339292"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610716"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2024.119156"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1088\/2631-8695\/ad681a"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636301"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2025.3547047"},{"key":"ref49","article-title":"USIM and u0: A vision-language-action dataset and model for general underwater robots","author":"Gu","year":"2025","journal-title":"arXiv:2510.07869"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3619794"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/YAC66630.2025.11149709"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01712"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11513504.pdf?arnumber=11513504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T23:00:45Z","timestamp":1780009245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11513504\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3691390","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}