{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T08:56:41Z","timestamp":1767085001418,"version":"3.37.3"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"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":["51979228","52102469"],"award-info":[{"award-number":["51979228","52102469"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Electron."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tie.2023.3337547","type":"journal-article","created":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T18:48:51Z","timestamp":1702406931000},"page":"11009-11018","source":"Crossref","is-referenced-by-count":3,"title":["Hierarchical Reinforcement Learning-Based End-to-End Visual Servoing With Smooth Subgoals"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4671-8371","authenticated-orcid":false,"given":"Yaozhen","family":"He","sequence":"first","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"}]},{"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4620-8993","authenticated-orcid":false,"given":"Huiping","family":"Li","sequence":"additional","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"}]},{"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0634-6734","authenticated-orcid":false,"given":"Yufeng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.250573"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2021.11.009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/70.760345"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2994002"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3235586"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197196"},{"key":"ref7","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nachum","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2865004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.2991147"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2019.2908923"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.03.049"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2022.105314"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3057005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3212411"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341756"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI51031.2022.10022285"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2018.2877499"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3111416"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2019.2899476"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594249"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2018.8453449"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2018.8482830"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2022.3211246"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2022.3211246"},{"key":"ref26","article-title":"Low-level autonomous control and tracking of quadrotor using reinforcement learning - sciencedirect","volume":"95","author":"Chp","year":"2020","journal-title":"Control Eng. Pract."},{"key":"ref27","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bellemare","year":"2016"},{"key":"ref28","article-title":"Exploration: A study of count-based exploration for deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tang","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"article-title":"Exploration by random network distillation","year":"2018","author":"Burda","key":"ref30"},{"article-title":"Incentivizing exploration in reinforcement learning with deep predictive models","year":"2015","author":"Stadie","key":"ref31"},{"article-title":"Never give up: Learning directed exploration strategies","year":"2020","author":"Badia","key":"ref32"},{"key":"ref33","first-page":"507","article-title":"Agent57: Outperforming the Atari human benchmark","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Badia","year":"2020"},{"article-title":"Go-explore: A new approach for hard-exploration problems","year":"2019","author":"Ecoffet","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3048668"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2016.2617464"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3256724"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adc8892"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968225"},{"key":"ref41","first-page":"3191","article-title":"Proximal policy optimization algorithms","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Schulman","year":"2017"},{"key":"ref42","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","year":"2018"},{"key":"ref43","first-page":"834","article-title":"Improving stochastic policy gradients in continuous control with deep reinforcement learning using the beta distribution","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chou","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3273687"},{"article-title":"The MNIST database of handwritten digits","year":"1998","author":"LeCun","key":"ref45"}],"container-title":["IEEE Transactions on Industrial Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/41\/10547605\/10354441.pdf?arnumber=10354441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T04:55:32Z","timestamp":1717649732000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10354441\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":45,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tie.2023.3337547","relation":{},"ISSN":["0278-0046","1557-9948"],"issn-type":[{"type":"print","value":"0278-0046"},{"type":"electronic","value":"1557-9948"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}