{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T05:11:59Z","timestamp":1775365919242,"version":"3.50.1"},"reference-count":69,"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 Funds for Distinguished Young Scholar","doi-asserted-by":"publisher","award":["62325307"],"award-info":[{"award-number":["62325307"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation Major Scientific Research Instrument Development Project","doi-asserted-by":"publisher","award":["62527809"],"award-info":[{"award-number":["62527809"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Key Industry Research and Development Program","award":["ZDCY20250901102300001"],"award-info":[{"award-number":["ZDCY20250901102300001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373257"],"award-info":[{"award-number":["62373257"]}],"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":["62473264"],"award-info":[{"award-number":["62473264"]}],"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":["62203134"],"award-info":[{"award-number":["62203134"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023B1515120038"],"award-info":[{"award-number":["2023B1515120038"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010877","name":"Science, Technology and Innovation Commission of Shenzhen Municipality","doi-asserted-by":"publisher","award":["KJZD20230923113801004"],"award-info":[{"award-number":["KJZD20230923113801004"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Project of State Key Laboratory of Synthetical Automation for Process Industries","award":["SAPI-2025-KFKT-11"],"award-info":[{"award-number":["SAPI-2025-KFKT-11"]}]},{"name":"Research and Application of Bipedal Humanoid Robots for Industrial Scenarios Guangdong Province Key Area Research and Development Program","award":["2025B0909020002"],"award-info":[{"award-number":["2025B0909020002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3668970","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:52:19Z","timestamp":1772225539000},"page":"5732-5743","source":"Crossref","is-referenced-by-count":1,"title":["Toward Reliable Imitation Learning With Limited Expert Demonstrations via Search-Based Inverse Dynamic Learning"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1864-9440","authenticated-orcid":false,"given":"Zhiliang","family":"Lin","sequence":"first","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0336-1181","authenticated-orcid":false,"given":"Zhuangzhuang","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4843-2739","authenticated-orcid":false,"given":"Guanming","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8707-3269","authenticated-orcid":false,"given":"Li","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2208-962X","authenticated-orcid":false,"given":"Jianqiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"CCIL: Continuity-based data augmentation for corrective imitation learning","author":"Ke","year":"2023","journal-title":"arXiv:2310.12972"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3352580"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3378915"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3337230"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3541768"},{"key":"ref6","first-page":"1","article-title":"Born to learn: What infants learn from watching us","author":"Meltzoff","year":"1999","journal-title":"The Role of Early Experience in Infant Development"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3403833"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3347264"},{"key":"ref11","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3274536"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adt0187"},{"key":"ref14","first-page":"143","article-title":"DART: Noise injection for robust imitation learning","volume-title":"Proc. Conf. robot Learn.","author":"Laskey"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3834"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref17","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3441816"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2025.3576871"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3535764"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00284"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/math10091551"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3573191"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3552832"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1985.1087242"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1436"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref29","first-page":"305","article-title":"ALVINN, an autonomous land vehicle in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"1","author":"Pomerleau"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33705"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2025.3546563"},{"key":"ref33","first-page":"21810","article-title":"MOReL: Model-based offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kidambi"},{"key":"ref34","first-page":"965","article-title":"Mitigating covariate shift in imitation learning via offline data with partial coverage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111032"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34099"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1201\/9781420049503-c37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.9734\/ajrcos\/2025\/v18i3584"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3544585.3544600"},{"key":"ref40","volume-title":"Pruning Duplicate Nodes in Depth-First Search","author":"Taylor","year":"1997"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/c2009-0-16511-x"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/361002.361007"},{"key":"ref43","article-title":"SEABO: A simple search-based method for offline imitation learning","author":"Lyu","year":"2024","journal-title":"arXiv:2402.03807"},{"key":"ref44","article-title":"Five balltree construction algorithms","author":"Omohundro","year":"1989"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/4908.003.0008"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"ref47","first-page":"18353","article-title":"BAIL: Best-action imitation learning for batch deep reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen"},{"key":"ref48","first-page":"6288","article-title":"Exponentially weighted imitation learning for batched historical data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Wang"},{"key":"ref49","article-title":"Boosting offline reinforcement learning via data rebalancing","author":"Yue","year":"2022","journal-title":"arXiv:2210.09241"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06392-z"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561915"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref53","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume":"33","author":"Laskin","year":"2020","journal-title":"Adv. neural Inf. Process. Syst."},{"key":"ref54","first-page":"1","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kostrikov"},{"key":"ref55","first-page":"907","article-title":"S4rl: Surprisingly simple self-supervision for offline reinforcement learning in robotics","volume-title":"Proc. Conf. Robot Learn.","author":"Sinha"},{"key":"ref56","first-page":"46323","article-title":"Synthetic experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref57","article-title":"DiffStitch: Boosting offline reinforcement learning with diffusion-based trajectory stitching","author":"Li","year":"2024","journal-title":"arXiv:2402.02439"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1808"},{"key":"ref59","article-title":"Optimal transport for offline imitation learning","author":"Luo","year":"2023","journal-title":"arXiv:2303.13971"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/882"},{"key":"ref61","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Sohn"},{"key":"ref62","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018","journal-title":"arXiv:1802.09464"},{"key":"ref63","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630771"},{"key":"ref67","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":"ref68","article-title":"Learning self-correctable policies and value functions from demonstrations with negative sampling","author":"Luo","year":"2019","journal-title":"arXiv:1907.05634"},{"key":"ref69","article-title":"Safety, robustness, and interpretability in machine learning","author":"Pfrommer","year":"2025"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11417181.pdf?arnumber=11417181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T19:56:41Z","timestamp":1773431801000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11417181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3668970","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}