{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T12:46:30Z","timestamp":1783514790281,"version":"3.55.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006965","name":"Telemedicine and Advanced Technology Research Center","doi-asserted-by":"publisher","award":["NSF2045803"],"award-info":[{"award-number":["NSF2045803"]}],"id":[{"id":"10.13039\/100006965","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/lra.2025.3627088","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:13:34Z","timestamp":1761930814000},"page":"13145-13152","source":"Crossref","is-referenced-by-count":4,"title":["SurgIRL: Toward Life-Long Learning for Surgical Automation by Incremental Reinforcement Learning"],"prefix":"10.1109","volume":"10","author":[{"given":"Yun-Jie","family":"Ho","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering Department, University of California San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9322-5174","authenticated-orcid":false,"given":"Zih-Yun","family":"Chiu","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, University of California San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4714-3028","authenticated-orcid":false,"given":"Yuheng","family":"Zhi","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, University of California San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9689-0172","authenticated-orcid":false,"given":"Michael C.","family":"Yip","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, University of California San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s00464-024-10788-w"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630582"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487611"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3031236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636432"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR63436.2024.10585751"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3056057"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561624"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3421191"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR48346.2021.9661514"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/BioRob60516.2024.10719948"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2018.8560468"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1142\/S2424905X21400031"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160510"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0188233"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaz7597"},{"key":"ref17","first-page":"13590","article-title":"Flexible attention-based multi-policy fusion for efficient deep reinforcement learning","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Chiu","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610263"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801845"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461200"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49439.2021.9551453"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812393"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794159"},{"key":"ref24","first-page":"130","article-title":"Surgical robot transformer (SRT): Imitation learning for surgical tasks","volume-title":"Proc. Conf. Robot Learn.","author":"Kim","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610059"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2018.8441801"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SYSCON.2019.8836924"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636175"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3227873"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3254860"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2023.3237772"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN47096.2020.9223543"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196588"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561673"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3266720"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR58858.2023.10406708"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3410297"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-022-02630-2"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636193"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3351797"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160327"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR57123.2023.10130214"},{"key":"ref43","article-title":"Categorical reparameterization with Gumbel-Softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang","year":"2017"},{"key":"ref44","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":"ref45","article-title":"Decoupling exploration and exploitation in reinforcement learning","volume-title":"Proc. Workshop Unsupervised Reinforcement Learn.","author":"Schfer","year":"2021"},{"key":"ref46","article-title":"Budgeted training: Rethinking deep neural network training under resource constraints","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106796"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635867"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907809"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3111441"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981966"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161291"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00304"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.01.005"},{"key":"ref56","first-page":"496","article-title":"Scaling cross-embodied learning: One policy for manipulation, navigation, locomotion and aviation","volume-title":"Proc. Conf. Robot Learn.","author":"Doshi","year":"2025"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/11215960\/11223235-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11215960\/11223235.pdf?arnumber=11223235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T19:02:03Z","timestamp":1764010923000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11223235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":56,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3627088","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}