{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:22:47Z","timestamp":1790875367826,"version":"4.1.0"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":["62003343"],"award-info":[{"award-number":["62003343"]}],"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":["62222316"],"award-info":[{"award-number":["62222316"]}],"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":["U1913601"],"award-info":[{"award-number":["U1913601"]}],"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":["62073325"],"award-info":[{"award-number":["62073325"]}],"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":["U20A20224"],"award-info":[{"award-number":["U20A20224"]}],"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":["U1913210"],"award-info":[{"award-number":["U1913210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["M22008"],"award-info":[{"award-number":["M22008"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2020140"],"award-info":[{"award-number":["2020140"]}],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CIE-Tencent Robotics X Rhino-Bird Focused Research Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Electron."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tie.2023.3310021","type":"journal-article","created":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T17:55:27Z","timestamp":1695059727000},"page":"7722-7731","source":"Crossref","is-referenced-by-count":18,"title":["CASOG: Conservative Actor\u2013Critic With SmOoth Gradient for Skill Learning in Robot-Assisted Intervention"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1948-8283","authenticated-orcid":false,"given":"Hao","family":"Li","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7602-4848","authenticated-orcid":false,"given":"Xiao-Hu","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6227-4811","authenticated-orcid":false,"given":"Xiao-Liang","family":"Xie","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1790-8448","authenticated-orcid":false,"given":"Shi-Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8964-7844","authenticated-orcid":false,"given":"Zhen-Qiu","family":"Feng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1534-5840","authenticated-orcid":false,"given":"Zeng-Guang","family":"Hou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2019.10.009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-013-0946-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/ccd.27173"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/ccd.25927"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcin.2010.12.007"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2896763"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1515\/cdbme-2020-0007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574722001527"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3135277"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196912"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2004.842673"},{"key":"ref12","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00708-4"},{"key":"ref14","first-page":"1518","article-title":"Actionable models: Unsupervised offline reinforcement learning of robotic skills","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Chebotar","year":"2021"},{"key":"ref15","first-page":"2633","article-title":"BDD100 K: A diverse driving dataset for heterogeneous multitask learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Yu","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref17","first-page":"1154","article-title":"Offline reinforcement learning from images with latent space models","volume-title":"Proc. 3rd Annu. Conf. Learn. Dyn. Control","author":"Rafailov","year":"2021"},{"key":"ref18","article-title":"PCI trainer for beginners","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC46164.2021.9629943"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560838"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63830-6_16"},{"key":"ref22","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref23","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref24","first-page":"2784","article-title":"Stabilizing off-policy deep reinforcement learning from pixels","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Cetin","year":"2022"},{"key":"ref25","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Kumar","year":"2020"},{"key":"ref26","first-page":"3852","article-title":"Adversarially trained actor critic for offline reinforcement learning","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Cheng","year":"2022"},{"key":"ref27","first-page":"28954","article-title":"COMBO: Conservative offline model-based policy optimization","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Yu","year":"2021"},{"key":"ref28","article-title":"Prioritized experience replay","author":"Schaul","year":"2016"},{"key":"ref29","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40763-5_46"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16449-1_6"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.34133\/2022\/9759504"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.34133\/2022\/9783517"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.01.126"}],"container-title":["IEEE Transactions on Industrial Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/41\/10498107\/10254299.pdf?arnumber=10254299","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:47:40Z","timestamp":1725904060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10254299\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":37,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tie.2023.3310021","relation":{},"ISSN":["0278-0046","1557-9948"],"issn-type":[{"value":"0278-0046","type":"print"},{"value":"1557-9948","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}