{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T17:17:26Z","timestamp":1791047846539,"version":"4.1.0"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Ministry of Education Academic Research Fund Tier 1","award":["R265-000-614-114"],"award-info":[{"award-number":["R265-000-614-114"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1109\/lra.2019.2891311","type":"journal-article","created":{"date-parts":[[2019,1,8]],"date-time":"2019-01-08T22:17:26Z","timestamp":1546985846000},"page":"485-492","source":"Crossref","is-referenced-by-count":59,"title":["Robot-Assisted Training in Laparoscopy Using Deep Reinforcement Learning"],"prefix":"10.1109","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3555-7143","authenticated-orcid":false,"given":"Xiaoyu","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chin-Boon","family":"Chng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kah-Bin","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9463-4781","authenticated-orcid":false,"given":"Chee-Kong","family":"Chui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00464-014-3931-x"},{"key":"ref11","first-page":"426","article-title":"Data-derived models for segmentation with application to surgical assessment and training","author":"varadarajan","year":"0","journal-title":"Proc Int Conf Med Image Comput Comput -Assisted Intervention Springer"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-015-1194-1"},{"key":"ref13","article-title":"Machine learning approach for skill evaluation in robotic-assisted surgery","volume":"1","author":"fard","year":"0","journal-title":"Proc World Congr Eng Comput Sci"},{"key":"ref14","first-page":"11","article-title":"Laparoscopy training in united states obstetric and gynecology residency programs","volume":"10","author":"stovall","year":"2006","journal-title":"J Soc Laparoendoscopic Surgeons"},{"key":"ref15","article-title":"Multi-level discovery of deep options","author":"fox","year":"2017","journal-title":"arXiv 1703 08294"},{"key":"ref16","first-page":"418","article-title":"DDCO: Discovery of deep continuous options for robot learning from demonstrations","author":"krishnan","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(01)00174-1"},{"key":"ref18","article-title":"Rapidly-exploring random trees: progress and prospects","author":"lavalle","year":"2000","journal-title":"Algorithmic and Computational Robotics New Directions"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref28","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"0","journal-title":"Proc 11th USENIX Conf Operating Syst Des Implementation"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0039-6109(03)00164-6"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0090-4295(01)01423-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1089\/end.2009.0489"},{"key":"ref29","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"0","journal-title":"Proc 23rd AAAI Conf Artif Intell"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1089\/end.2009.0190"},{"key":"ref8","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"0","journal-title":"Proc Adv Neural Inf Process Syst Conf"},{"key":"ref7","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1055\/s-2002-19857"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_142-1"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjsurg.2009.05.008"},{"key":"ref20","first-page":"1","article-title":"Guided policy search","author":"levine","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref23","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3099564.3099567"},{"key":"ref25","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"0","journal-title":"Proc Adv Neural Inf Process Syst Conf"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8581687\/08604070.pdf?arnumber=8604070","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:04:47Z","timestamp":1657746287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8604070\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":29,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2019.2891311","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4]]}}}