{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:05:55Z","timestamp":1783530355353,"version":"3.55.0"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004853","name":"CUHK T Stone Robotics Institute, Hong Kong Innovation and Technology Commission","doi-asserted-by":"publisher","award":["ITS\/237\/21FP"],"award-info":[{"award-number":["ITS\/237\/21FP"]}],"id":[{"id":"10.13039\/501100004853","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160327","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"4640-4647","source":"Crossref","is-referenced-by-count":30,"title":["Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot"],"prefix":"10.1109","author":[{"given":"Tao","family":"Huang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Computer Science and Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Computer Science and Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun-Hui","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Dou","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Computer Science and Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2021.3101646"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49439.2021.9551569"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN47096.2020.9223543"},{"key":"ref4","article-title":"Robotic surgery with lean reinforcement learning","author":"Barnoy","year":"2021","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3203631"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2018.8560468"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/robotics3030310"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abj2908"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341710"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636175"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989275"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT.2019.8755235"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SYSCON.2019.8836924"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196588"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196912"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636193"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2021.3133075"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891311"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2980158"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-022-02630-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10085-1"},{"key":"ref22","article-title":"Guided policy search","volume-title":"International Conference on Machine Learning (ICML)","author":"Levine"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref24","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecer\u00edk","year":"2017","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.009"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR48346.2021.9661514"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794102"},{"key":"ref32","article-title":"Rrl: Resnet as representation for reinforcement learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Shah"},{"key":"ref33","first-page":"465","article-title":"Integrating behavior cloning and reinforcement learning for improved performance in dense and sparse reward environments","volume-title":"International Conference on Autonomous Agents and MultiAgent Systems (AAMAS)","author":"Goecks"},{"key":"ref34","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International Conference on Machine Learning (ICML)","author":"Fujimoto"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561673"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635867"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2014.2302385"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013914"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR.2018.8333301"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139344"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1142\/9789813232266_0010"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834116"},{"key":"ref47","article-title":"Generative adversarial imitation learning","author":"Ho","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref48","article-title":"Goal-conditioned imitation learning","author":"Ding","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref49","article-title":"Maximum entropy inverse reinforcement learning","author":"Ziebart","year":"2008","journal-title":"Association for the Advancement of Artificial Intelligence (AAAI)"},{"key":"ref50","article-title":"Learning robust rewards with adverserial inverse reinforcement learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Fu"},{"key":"ref51","article-title":"Discriminator-actor-critic: Addressing sample inefficiency and reward bias in adversarial imitation learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kostrikov"},{"key":"ref52","article-title":"Offline reinforcement learning with fisher divergence critic regularization","volume-title":"International Conference on Machine Learning (ICML)","author":"Kostrikov"},{"key":"ref53","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International Conference on Machine Learning (ICML)","author":"Fujimoto"},{"key":"ref54","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning (ICML)","author":"Haarnoja"},{"key":"ref55","article-title":"Awac: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-017-2053-3_2"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.010"},{"key":"ref59","article-title":"Hierarchical few-shot imitation with skill transition models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hakhamaneshi"},{"key":"ref60","article-title":"Dexterous imitation made easy: A learning-based framework for efficient dexterous manipulation","author":"Arunachalam","year":"2022","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Continuous control with deep reinforcement learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lillicrap"},{"key":"ref62","article-title":"Openai baselines","author":"Dhariwal","year":"2017"},{"key":"ref63","article-title":"On pathologies in kl-regularized reinforcement learning from expert demonstrations","author":"Rudner","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref65","article-title":"Hindsight experience replay","author":"Andrychowicz","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref67","article-title":"Sqil: Imitation learning via reinforcement learning with sparse rewards","volume-title":"International Conference on Learning Representations (ICLR)","author":"Reddy"},{"key":"ref68","article-title":"Curl: Contrastive unsupervised representations for reinforcement learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Laskin"},{"key":"ref69","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"International Conference on Learning Representations (ICLR)","author":"Yarats"},{"key":"ref70","article-title":"Deep reinforcement learning at the edge of the statistical precipice","author":"Agarwal","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160327.pdf?arnumber=10160327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T03:58:10Z","timestamp":1710388690000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160327\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160327","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}