{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T15:00:19Z","timestamp":1776956419699,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100012913","name":"Tata Consultancy Services","doi-asserted-by":"publisher","award":["Grant"],"award-info":[{"award-number":["Grant"]}],"id":[{"id":"10.13039\/100012913","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009481","name":"Tata Sons","doi-asserted-by":"publisher","award":["Grant"],"award-info":[{"award-number":["Grant"]}],"id":[{"id":"10.13039\/501100009481","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Titan","award":["Grant"],"award-info":[{"award-number":["Grant"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2143109"],"award-info":[{"award-number":["IIS-2143109"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,16]]},"DOI":"10.1145\/3757279.3785630","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:27:38Z","timestamp":1773102458000},"page":"1040-1049","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Learning Human Preferences over a Human-Robot Collaboration Based on Explicit and Implicit Human Feedback"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0152-053X","authenticated-orcid":false,"given":"Kate","family":"Candon","sequence":"first","affiliation":[{"name":"Yale University, New Haven, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8535-2771","authenticated-orcid":false,"given":"Qiping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8557-3348","authenticated-orcid":false,"given":"Alexander","family":"Lew","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6292-4706","authenticated-orcid":false,"given":"Houston","family":"Claure","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9753-154X","authenticated-orcid":false,"given":"Lena","family":"Qian","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3060-1745","authenticated-orcid":false,"given":"Alyssa","family":"Quarles","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4777-2086","authenticated-orcid":false,"given":"Chayan","family":"Sarkar","sequence":"additional","affiliation":[{"name":"TCS Research, New Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0698-5472","authenticated-orcid":false,"given":"Marynel","family":"V\u00e1zquez","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"William Bradley Knox, and Todd Kulesza","author":"Amershi Saleema","year":"2014","unstructured":"Saleema Amershi, Maya Cakmak, William Bradley Knox, and Todd Kulesza. 2014. Power to the people: The role of humans in interactive machine learning. AI magazine, 35, 4 (2014), 105\u2013120."},{"key":"e_1_3_2_2_2_1","volume-title":"A survey of robot learning from demonstration. Robotics and autonomous systems, 57, 5","author":"Argall Brenna D","year":"2009","unstructured":"Brenna D Argall, Sonia Chernova, Manuela Veloso, and Brett Browning. 2009. A survey of robot learning from demonstration. Robotics and autonomous systems, 57, 5 (2009), 469\u2013483."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAD65464.2025.11114031"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2009.07.005"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8659"},{"key":"e_1_3_2_2_6_1","first-page":"423","article-title":"Reinforcement learning: An introduction. by richard\u2019s sutton","volume":"6","author":"Barto Andrew G","year":"2021","unstructured":"Andrew G Barto. 2021. Reinforcement learning: An introduction. by richard\u2019s sutton. SIAM Rev, 6, 2 (2021), 423.","journal-title":"SIAM Rev"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610977.3634987"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3576983"},{"key":"e_1_3_2_2_9_1","volume-title":"Behavioral overlays for non-verbal communication expression on a humanoid robot. Autonomous robots, 22","author":"Brooks Andrew G","year":"2007","unstructured":"Andrew G Brooks and Ronald C Arkin. 2007. Behavioral overlays for non-verbal communication expression on a humanoid robot. Autonomous robots, 22 (2007), 55\u201374."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3576980"},{"key":"e_1_3_2_2_11_1","unstructured":"Lawrence Chan Andrew Critch and Anca Dragan. 2021. Human irrationality: both bad and good for reward inference. arXiv preprint arXiv:2111.06956."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3171221.3171264"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780199842193.001.0001"},{"key":"e_1_3_2_2_14_1","volume-title":"Deep reinforcement learning from human preferences. Advances in neural information processing systems, 30","author":"Christiano Paul F","year":"2017","unstructured":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems, 30 (2017)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Michele Colledanchise and Petter \u00d6gren. 2018. Behavior Trees in Robotics and AI. isbn:9780429950902","DOI":"10.1201\/9780429489105"},{"key":"e_1_3_2_2_16_1","unstructured":"Yuchen Cui Qiping Zhang Alessandro Allievi Peter Stone Scott Niekum and W. Bradley Knox. 2020. The EMPATHIC Framework for Task Learning from Implicit Human Feedback. In CoRL."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2010.940150"},{"key":"e_1_3_2_2_18_1","volume-title":"6th Annual Conference on Robot Learning.","author":"Fitzgerald Tesca","year":"2022","unstructured":"Tesca Fitzgerald, Pallavi Koppol, Patrick Callaghan, Russell Quinlan Jun Hei Wong, Reid Simmons, Oliver Kroemer, and Henny Admoni. 2022. INQUIRE: INteractive querying for user-aware informative REasoning. In 6th Annual Conference on Robot Learning."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25740"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793898"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597512.3597518"},{"key":"e_1_3_2_2_22_1","unstructured":"Dylan Hadfield-Menell Stuart J Russell Pieter Abbeel and Anca Dragan. 2016. Cooperative inverse reinforcement learning. In Advances in neural information processing systems. 29."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487760"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642806"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"e_1_3_2_2_26_1","volume-title":"Reward learning from human preferences and demonstrations in atari. Advances in neural information processing systems, 31","author":"Ibarz Borja","year":"2018","unstructured":"Borja Ibarz, Jan Leike, Tobias Pohlen, Geoffrey Irving, Shane Legg, and Dario Amodei. 2018. Reward learning from human preferences and demonstrations in atari. Advances in neural information processing systems, 31 (2018)."},{"key":"e_1_3_2_2_27_1","volume-title":"Ashok Dara, and SankaranarayanaSamy K.","author":"Inkulu Anil Kumar","year":"2022","unstructured":"Anil Kumar Inkulu, MVA Raju Bahubalendruni, Ashok Dara, and SankaranarayanaSamy K. 2022. Challenges and opportunities in human robot collaboration context of Industry 4.0-a state of the art review. Industrial Robot: the international journal of robotics research and application, 49, 2 (2022), 226\u2013239."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509734"},{"key":"e_1_3_2_2_29_1","first-page":"4415","article-title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","volume":"33","author":"Jeon Hong Jun","year":"2020","unstructured":"Hong Jun Jeon, Smitha Milli, and Anca Dragan. 2020. Reward-rational (implicit) choice: A unifying formalism for reward learning. Advances in Neural Information Processing Systems, 33 (2020), 4415\u20134426.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"e_1_3_2_2_31_1","volume-title":"Michael L Walters, and Kerstin Dautenhahn.","author":"Koay Kheng Lee","year":"2009","unstructured":"Kheng Lee Koay, Dag Sverre Syrdal, Michael L Walters, and Kerstin Dautenhahn. 2009. Five weeks in the robot house\u2013exploratory human-robot interaction trials in a domestic setting. In 2009 second international conferences on advances in computer-human interactions. 219\u2013226."},{"key":"e_1_3_2_2_32_1","volume-title":"Analyzing the effects of human-aware motion planning on close-proximity human\u2013robot collaboration. Human factors, 57, 1","author":"Lasota Przemyslaw A","year":"2015","unstructured":"Przemyslaw A Lasota and Julie A Shah. 2015. Analyzing the effects of human-aware motion planning on close-proximity human\u2013robot collaboration. Human factors, 57, 1 (2015), 21\u201333."},{"key":"e_1_3_2_2_33_1","volume-title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1).","author":"Lee Kimin","year":"2021","unstructured":"Kimin Lee, Laura Smith, Anca Dragan, and Pieter Abbeel. 2021. B-Pref: Benchmarking Preference-Based Reinforcement Learning. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)."},{"key":"e_1_3_2_2_34_1","unstructured":"Jia-Min Li Ke-Xi Liu Ji-Fei Xie and Hao-Yu Wu. 2024. How Does Human\u2013Robot Collaboration Affect Hotel Employees\u2019 Proactive Behavior? International Journal of Human\u2013Computer Interaction 1\u201315."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211050958"},{"key":"e_1_3_2_2_36_1","volume-title":"Conference on Robot Learning. 123\u2013132","author":"Losey Dylan P","year":"2018","unstructured":"Dylan P Losey and Marcia K O\u2019Malley. 2018. Including uncertainty when learning from human corrections. In Conference on Robot Learning. 123\u2013132."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161261"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.3390\/robotics8040100"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2021.102231"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1514095.1514109"},{"key":"e_1_3_2_2_41_1","volume-title":"Conference on robot learning. 342\u2013352","author":"Myers Vivek","year":"2022","unstructured":"Vivek Myers, Erdem Biyik, Nima Anari, and Dorsa Sadigh. 2022. Learning multimodal rewards from rankings. In Conference on robot learning. 342\u2013352."},{"key":"e_1_3_2_2_42_1","unstructured":"Austin Narcomey Nathan Tsoi Ruta Desai and Marynel V\u00e1zquez. 2024. Learning human preferences over robot behavior as soft planning constraints. arXiv preprint arXiv:2403.19795."},{"key":"e_1_3_2_2_43_1","unstructured":"Carl Oechsner Sven Mayer and Andreas Butz. 2022. Challenges and Opportunities of Cooperative Robots as Cooking Appliances.. AutomationXP@ CHI."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316782.3316791"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889616"},{"key":"e_1_3_2_2_46_1","volume-title":"Human\u2013robot interaction: status and challenges. Human factors, 58, 4","author":"Sheridan Thomas B","year":"2016","unstructured":"Thomas B Sheridan. 2016. Human\u2013robot interaction: status and challenges. Human factors, 58, 4 (2016), 525\u2013532."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"crossref","unstructured":"Herbert A Simon. 1955. A behavioral model of rational choice. The quarterly journal of economics 99\u2013118.","DOI":"10.2307\/1884852"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhm.2022.103220"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3576990"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/1753326.1753693"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801889"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.09.009"},{"key":"e_1_3_2_2_53_1","volume-title":"Shutter: A Low-Cost and Flexible Social Robot Platform for In-the-Wild Deployments. In Companion of the 2024 ACM\/IEEE International Conference on Human-Robot Interaction (HRI \u201924)","author":"Thompson Sydney","year":"2024","unstructured":"Sydney Thompson, Austin Narcomey, Alexander Lew, and Marynel V\u00e1zquez. 2024. Shutter: A Low-Cost and Flexible Social Robot Platform for In-the-Wild Deployments. In Companion of the 2024 ACM\/IEEE International Conference on Human-Robot Interaction (HRI \u201924). 94\u201396."},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461778.3462101"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.3390\/technologies6020049"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3007109"},{"key":"e_1_3_2_2_57_1","first-page":"1","article-title":"A survey of preference-based reinforcement learning methods","volume":"18","author":"Wirth Christian","year":"2017","unstructured":"Christian Wirth, Riad Akrour, Gerhard Neumann, and Johannes F\u00fcrnkranz. 2017. A survey of preference-based reinforcement learning methods. Journal of Machine Learning Research, 18, 136 (2017), 1\u201346.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_58_1","volume-title":"Reconsidering Scalar Feedback in Interactive Reinforcement Learning. In 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 4121\u20134128","author":"Yu Hang","year":"2023","unstructured":"Hang Yu, Reuben M Aronson, Katherine H Allen, and Elaine Schaertl Short. 2023. From \u201cThumbs Up\u201d to \u201c10 out of 10\u201d: Reconsidering Scalar Feedback in Interactive Reinforcement Learning. In 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 4121\u20134128."},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3576986"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3719020"},{"key":"e_1_3_2_2_61_1","volume-title":"Learning Human Contribution Preferences in Collaborative Human-Robot Tasks. In Conference on Robot Learning. 3597\u20133618","author":"Zhao Michelle D","year":"2023","unstructured":"Michelle D Zhao, Reid Simmons, and Henny Admoni. 2023. Learning Human Contribution Preferences in Collaborative Human-Robot Tasks. In Conference on Robot Learning. 3597\u20133618."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.3390\/robotics7020017"}],"event":{"name":"HRI '26: 21st ACM\/IEEE International Conference on Human-Robot Interaction","location":"Edinburgh Scotland UK","acronym":"HRI '26","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction","IEEE RAS"]},"container-title":["Proceedings of the 21st ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3757279.3785630","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T00:30:20Z","timestamp":1773534620000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757279.3785630"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":62,"alternative-id":["10.1145\/3757279.3785630","10.1145\/3757279"],"URL":"https:\/\/doi.org\/10.1145\/3757279.3785630","relation":{},"subject":[],"published":{"date-parts":[[2026,3,16]]},"assertion":[{"value":"2026-03-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}