{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T18:25:07Z","timestamp":1772735107601,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/lra.2023.3300238","type":"journal-article","created":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T17:41:27Z","timestamp":1690825287000},"page":"5815-5822","source":"Crossref","is-referenced-by-count":11,"title":["Learning Robotic Insertion Tasks From Human Demonstration"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5955-9755","authenticated-orcid":false,"given":"Kaimeng","family":"Wang","sequence":"first","affiliation":[{"name":"FANUC Advanced Research Laboratory, FANUC America Corporation, Union City, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1045-9691","authenticated-orcid":false,"given":"Yu","family":"Zhao","sequence":"additional","affiliation":[{"name":"FANUC Advanced Research Laboratory, FANUC America Corporation, Union City, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ichiro","family":"Sakuma","sequence":"additional","affiliation":[{"name":"Department of Precision Engineering, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/AIM.2016.7576815"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206196"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2020.101996"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/app10196923"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASSPCC.2000.882463"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1108\/IR-07-2014-0363"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/s23052514"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2635479"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967325"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160275"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197124"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196104"},{"key":"ref14","first-page":"654","article-title":"Videodex: Learning dexterity from internet videos","volume-title":"Proc. Conf. Robot Learn.","author":"Shaw","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211046285"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-018-2788-x"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/s19204586"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12700"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2021.3059685"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01109"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1108\/IR-04-2022-0093"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363552"},{"key":"ref24","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Janner","year":"2019"},{"key":"ref25","article-title":"Randomized ensembled double Q-learning: Learning fast without a model","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref26","article-title":"Dynamics-aware unsupervised discovery of skills","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sharma","year":"2019"},{"key":"ref27","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref28","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Vecerik","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref30","article-title":"Offline reinforcement learning with implicit Q-learning","volume-title":"Proc. Deep RL Workshop NeurIPS","author":"Kostrikov","year":"2021"},{"key":"ref31","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2019"},{"key":"ref32","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fujimoto","year":"2021"},{"key":"ref33","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/70.370511"},{"key":"ref35","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":"ref36","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst. Volume 2","author":"Sohn","year":"2015"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00088"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00533"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451022"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10185095\/10197579.pdf?arnumber=10197579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T16:24:52Z","timestamp":1709310292000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10197579\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":40,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3300238","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}