{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:20:39Z","timestamp":1766067639629,"version":"3.37.3"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0101100"],"award-info":[{"award-number":["2018AAA0101100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073160"],"award-info":[{"award-number":["62073160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981076","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"848-855","source":"Crossref","is-referenced-by-count":8,"title":["Task Decoupling in Preference-based Reinforcement Learning for Personalized Human-Robot Interaction"],"prefix":"10.1109","author":[{"given":"Mingjiang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Management and Engineering, Nanjing University,Department of Control and Systems Engineering,Nanjing,China"}]},{"given":"Chunlin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Management and Engineering, Nanjing University,Department of Control and Systems Engineering,Nanjing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3161588"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aat7451"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref6","article-title":"A bayesian approach for policy learning from trajectory preference queries","volume":"25","author":"Wilson","year":"2012","journal-title":"Adv. Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5313-8"},{"key":"ref8","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Adv. Neural Information Processing Systems"},{"issue":"136","key":"ref9","first-page":"1","article-title":"A survey of preference-based reinforcement learning methods","volume":"18","author":"Wirth","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","first-page":"6152","article-title":"Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and un-supervised pre-training","volume-title":"Int. Conf. Machine Learning","author":"Lee"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-019-09865-0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aao6760"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2784832"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-019-00560-9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3277903"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196661"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341416"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33486-3_8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.023"},{"key":"ref20","article-title":"Reward learning from human preferences and demonstrations in atari","volume":"31","author":"Ibarz","year":"2018","journal-title":"Adv. Neural Information Processing Systems"},{"article-title":"Reward uncertainty for exploration in preference-based reinforcement learning","volume-title":"Deep RL Workshop NeurIPS","author":"Liang","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3063927"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084198"},{"article-title":"Surf: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based rein-forcement learning","volume-title":"Deep RL Workshop NeurIPS","author":"Park","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref28","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Int. conf. Machine Learning","author":"Haarnoja"},{"key":"ref29","article-title":"B-pref: Benchmarking preference-based reinforcement learning","author":"Lee","year":"2021","journal-title":"Adv. Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197411"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981076.pdf?arnumber=9981076","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T08:34:51Z","timestamp":1709368491000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981076\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981076","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}