{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:41:42Z","timestamp":1766061702384,"version":"3.48.0"},"reference-count":61,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247723","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"7981-7988","source":"Crossref","is-referenced-by-count":0,"title":["Towards Surgical Task Automation: Actor-Critic Models Meet Self-Supervised Imitation Learning\n                    <sup>*<\/sup>"],"prefix":"10.1109","author":[{"given":"Jingshuai","family":"Liu","sequence":"first","affiliation":[{"name":"the National Elite Institute of Engineering, Chongqing University,Embodied Intelligence Lab,Chongqing,China,401135"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alain","family":"Andres","sequence":"additional","affiliation":[{"name":"TECNALIA, Basque Research and Technology Alliance (BRTA),Donostia-San Sebastian,Spain,20009"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghang","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of Strathclyde,Centre for Precision Manufacturing,Department of Design, Manufacturing and Engineering Management,Glasgow,U.K.,G1 1XJ"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuning","family":"Du","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Institute for Imaging, Data and Communications, School of Engineering,Edinburgh,U.K.,EH9 3JE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xichun","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Strathclyde,Centre for Precision Manufacturing,Department of Design, Manufacturing and Engineering Management,Glasgow,U.K.,G1 1XJ"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenmiao","family":"Shu","sequence":"additional","affiliation":[{"name":"University of Strathclyde,Department of Biomedical Engineering,Glasgow,U.K.,G4 0NW"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Can","family":"Pu","sequence":"additional","affiliation":[{"name":"the National Elite Institute of Engineering, Chongqing University,Embodied Intelligence Lab,Chongqing,China,401135"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sotirios","family":"Tsaftaris","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Institute for Imaging, Data and Communications, School of Engineering,Edinburgh,U.K.,EH9 3JE"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-0638-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.surg.2020.11.040"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.surg.2020.04.049"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"3rd International Conference on Learning Representations (ICLR)","author":"Simonyan","key":"ref7"},{"key":"ref8","first-page":"2672","article-title":"Generative adversarial networks","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"article-title":"An image is worth 16x16 words: transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891311"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/15533506221095298"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3254860"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3227873"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-08896-5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00917-4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR57123.2023.10130214"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref19","first-page":"5308","article-title":"Integrating Behavior Cloning and Reinforcement Learning for Improved Performance in Dense and Sparse Reward Environments","author":"Vecerik","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"15339","article-title":"A Minimalist Approach to Offline Reinforcement Learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning","author":"Tarasov","year":"2023","journal-title":"Advances in Neural Information Processing Systems 36 (NeurIPS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/882"},{"key":"ref25","article-title":"Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification","author":"Eysenbach","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","article-title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","author":"Kim","year":"2022","journal-title":"NeurIPS"},{"key":"ref27","article-title":"Generative Adversarial Imitation Learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Generative adversarial imitation from observation","volume-title":"ICML Workshop","author":"Torabi","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"ref30","first-page":"18032","article-title":"SEABO: A Simple Search-Based Method for Offline Imitation Learning","author":"Yuan","year":"2020","journal-title":"NeurIPS"},{"key":"ref31","article-title":"Interpretable Generative Adversarial Imitation Learning","volume":"abs\/2402.10310","author":"Liu","year":"2024","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10108-x"},{"article-title":"Self-Imitation Learning","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML)","author":"Oh","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3284380"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196588"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636193"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2021.3133075"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-022-02630-2"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3266720"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342180"},{"key":"ref41","article-title":"SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards","author":"Reddy","year":"2020","journal-title":"ICLR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919880273"},{"key":"ref43","article-title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","author":"Fujimoto","year":"2020","journal-title":"ICML"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.129079"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160327"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/s21103409"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref48","first-page":"663","article-title":"Algorithms for Inverse Reinforcement Learning","author":"Ng","year":"2000","journal-title":"ICML"},{"key":"ref49","first-page":"1433","article-title":"Maximum Entropy Inverse Reinforcement Learning","volume-title":"AAAI Conference on Artificial Intelligence (AAAI-08)","author":"Ziebart"},{"key":"ref50","first-page":"14694","article-title":"Optimal Transport for Offline Imitation Learning","author":"Wei","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","first-page":"5048","article-title":"Hindsight Experience Replay","author":"Andrychowicz","year":"2017","journal-title":"NIPS"},{"key":"ref52","article-title":"Continuous Control with Deep Reinforcement Learning","author":"Lillicrap","year":"2016","journal-title":"ICLR May 2-4"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref54","first-page":"1587","article-title":"Addressing Function Approximation Error in Actor-Critic Methods","volume":"80","author":"Fujimoto","year":"2018","journal-title":"ICML"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2021.107527"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref57","article-title":"Off-Policy Deep Reinforcement Learning without Exploration","author":"Fujimoto","year":"2018","journal-title":"ICML"},{"key":"ref58","first-page":"5774","article-title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization","volume":"139","author":"Kostrikov","year":"2021","journal-title":"ICML"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635867"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834116"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247723.pdf?arnumber=11247723","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:39:04Z","timestamp":1766061544000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247723\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247723","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}