{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T13:57:18Z","timestamp":1768312638239,"version":"3.49.0"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Natural Science Foundation of Shenzhen","award":["JCYJ20230807111604008"],"award-info":[{"award-number":["JCYJ20230807111604008"]}]},{"name":"Natural Science Foundation of Shenzhen","award":["JCYJ20240813112007010"],"award-info":[{"award-number":["JCYJ20240813112007010"]}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515010003"],"award-info":[{"award-number":["2024A1515010003"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2022YFB4701400"],"award-info":[{"award-number":["2022YFB4701400"]}]},{"name":"Cross-disciplinary Fund for Research and Innovation","award":["JC2024002"],"award-info":[{"award-number":["JC2024002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/lra.2025.3588411","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T17:43:54Z","timestamp":1752601434000},"page":"9232-9239","source":"Crossref","is-referenced-by-count":1,"title":["Behavior Cloning Assisted Reinforcement Learning for Cable-Driven Continuum Space Robots in Sparse Reward Environments"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9366-5435","authenticated-orcid":false,"given":"Xianru","family":"Tian","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Xia","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8956-5408","authenticated-orcid":false,"given":"Junbo","family":"Tan","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2169-0007","authenticated-orcid":false,"given":"Bo","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, The University of Queensland, QLD, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiheng","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3507-9732","authenticated-orcid":false,"given":"Xueqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)AS.1943-5525.0001335"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO55434.2022.10012023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793653"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2019.105657"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241285161"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref7","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Icml","author":"Ng","year":"1999"},{"key":"ref8","article-title":"ALVINN: An autonomous land vehicle in a neural network","volume-title":"Adv. neural Inf. Process. Syst.","author":"Pomerleau","year":"1988"},{"key":"ref9","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/RoboSoft48309.2020.9116003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1108\/IR-01-2023-0002"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3097660"},{"key":"ref14","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.","author":"Haarnoja","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO49542.2019.8961852"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341378"},{"key":"ref17","article-title":"Hindsight experience replay","volume-title":"Adv. neural Inf. Process. Syst.","author":"Andrychowicz","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref21","article-title":"Algorithms for inverse reinforcement learning.","volume":"1","author":"Ng","year":"2000","journal-title":"Icml"},{"key":"ref22","first-page":"32","article-title":"Watch and match: Supercharging imitation with regularized optimal transport","volume-title":"Conf. Robot Learn.","author":"Haldar","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.009"},{"key":"ref24","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017"},{"key":"ref25","first-page":"1577","article-title":"Efficient online reinforcement learning with offline data","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Ball","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.056"},{"key":"ref27","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. Fourteenth Int. Conf. Artif. Intell. Statist.","author":"Ross","year":"2011"},{"key":"ref28","article-title":"Randomized ensembled double Q-learning: Learning fast without a model","author":"Chen","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2020.3013658"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11082640\/11078924.pdf?arnumber=11078924","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T17:45:58Z","timestamp":1754588758000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11078924\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":29,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3588411","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}