{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T02:01:31Z","timestamp":1740103291206,"version":"3.37.3"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,8]]},"DOI":"10.1109\/icarm62033.2024.10715884","type":"proceedings-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T17:27:32Z","timestamp":1729272452000},"page":"655-661","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid Reinforcement Learning based on Human Preference and Advice for Efficient Robot Skill Learning"],"prefix":"10.1109","author":[{"given":"Bingqian","family":"Li","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Research Center for Intelligent Robotics, School of Astronautics,Xi’an,China,710072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Liu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Research Center for Intelligent Robotics, School of Astronautics,Xi’an,China,710072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengxiong","family":"Liu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Research Center for Intelligent Robotics, School of Astronautics,Xi’an,China,710072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Panfeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Research Center for Intelligent Robotics, School of Astronautics,Xi’an,China,710072"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1177\/17298814211007305"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1177\/0278364913495721"},{"key":"ref3","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"Ng","year":"2000","journal-title":"Icml"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1016\/j.artint.2021.103500"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1145\/1597735.1597738"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ROMAN.2012.6343862"},{"key":"ref7","first-page":"292","article-title":"Tamer: Training an agent manually via evaluative reinforcement","volume-title":"ICDL","author":"Knox"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1016\/j.artint.2007.09.009"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1145\/2157689.2157693"},{"key":"ref10","article-title":"Deep reinforcement learning from human p","volume":"30","author":"Christiano","year":"2017","journal-title":"Adv. neural inf. process. syst"},{"volume-title":"Benchmarks and algorithms for offline preference-based reward learning","year":"2023","author":"Shin","key":"ref11"},{"key":"ref12","article-title":"Reward learning from human p and demonstrations in atari","volume":"31","author":"Ibarz","year":"2018","journal-title":"Adv. neural inf. process. syst"},{"key":"ref13","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume-title":"Icml","author":"Brown"},{"key":"ref14","article-title":"Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","author":"Lee","year":"2021","journal-title":"arXiv preprint arXiv:2106.05091"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.15607\/RSS.2017.XIII.053"},{"key":"ref16","first-page":"519","article-title":"Batch active preference-based learning of reward functions","author":"Biyik","year":"2018","journal-title":"CoRL"},{"key":"ref17","article-title":"Active preference-based gaussian process regression for reward learning","author":"B\u0131y\u0131k","year":"2020","journal-title":"arXiv preprint arXiv:2005.02575"},{"volume-title":"Surf: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning","year":"2022","author":"Park","key":"ref18"},{"volume-title":"ICML 2023 Workshop","author":"Verma","article-title":"Exploiting action distances for reward learning from human p","key":"ref19"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/IROS51168.2021.9636020"},{"key":"ref21","first-page":"101","article-title":"Learning agents for uncertain environments","volume-title":"COLT","author":"Russell"},{"key":"ref22","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","volume":"26","author":"Griffith","year":"2013","journal-title":"Adv. neural inf. process. syst"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1007\/s10846-018-0839-z"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1007\/978-3-319-29339-4_2"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1177\/0278364919871998"},{"key":"ref26","first-page":"1000","article-title":"Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance","volume-title":"AAAI","volume":"6","author":"Thomaz"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/TIE.2023.3294600"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/ICRA.2015.7138994"}],"event":{"name":"2024 International Conference on Advanced Robotics and Mechatronics (ICARM)","start":{"date-parts":[[2024,7,8]]},"location":"Tokyo, Japan","end":{"date-parts":[[2024,7,10]]}},"container-title":["2024 International Conference on Advanced Robotics and Mechatronics (ICARM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10715684\/10715739\/10715884.pdf?arnumber=10715884","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:34:27Z","timestamp":1736883267000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10715884\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,8]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icarm62033.2024.10715884","relation":{},"subject":[],"published":{"date-parts":[[2024,7,8]]}}}