{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:22:40Z","timestamp":1766067760514,"version":"build-2065373602"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T00:00:00Z","timestamp":1681862400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T00:00:00Z","timestamp":1681862400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council (NSERC) of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council (CSC)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,4,19]]},"DOI":"10.1109\/ismr57123.2023.10130214","type":"proceedings-article","created":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T17:28:15Z","timestamp":1685035695000},"page":"1-7","source":"Crossref","is-referenced-by-count":6,"title":["Towards Safe and Efficient Reinforcement Learning for Surgical Robots Using Real-Time Human Supervision and Demonstration"],"prefix":"10.1109","author":[{"given":"Yafei","family":"Ou","sequence":"first","affiliation":[{"name":"University of Alberta,Department of Electrical and Computer Engineering,Edmonton,Alberta,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahdi","family":"Tavakoli","sequence":"additional","affiliation":[{"name":"University of Alberta,Department of Electrical and Computer Engineering,Edmonton,Alberta,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561673"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341710"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2022.3170786"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3097660"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.31256\/HSMR2022.25"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793561"},{"key":"ref7","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","volume":"26","author":"Griffith","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11485"},{"key":"ref9","article-title":"Trial without error: Towards safe reinforcement learning via human intervention","author":"Saunders","year":"2017","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR48346.2021.9661514"},{"key":"ref12","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907809"},{"key":"ref14","first-page":"410","article-title":"Intervention aided reinforcement learning for safe and practical policy optimization in navigation","volume-title":"Conference on Robot Learning","author":"Wang"},{"key":"ref15","article-title":"Toward human-in-the-loop ai: Enhancing deep reinforcement learning via real-time human guidance for autonomous driving","volume-title":"Engineering","author":"Wu","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3177685"},{"key":"ref17","article-title":"Open-sourced reinforcement learning environments for surgical robotics","author":"Richter","year":"2019","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR48347.2022.9807609"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635867"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812010"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2525827"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s41315-016-0006-2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8122951"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2019.8779417"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2890674"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574719000651"},{"key":"ref27","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.01.016"}],"event":{"name":"2023 International Symposium on Medical Robotics (ISMR)","start":{"date-parts":[[2023,4,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2023,4,21]]}},"container-title":["2023 International Symposium on Medical Robotics (ISMR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10130140\/10130174\/10130214.pdf?arnumber=10130214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:25:16Z","timestamp":1705026316000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10130214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,19]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ismr57123.2023.10130214","relation":{},"subject":[],"published":{"date-parts":[[2023,4,19]]}}}