{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T11:20:34Z","timestamp":1773141634853,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2132887"],"award-info":[{"award-number":["IIS-2132887"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,24]]},"DOI":"10.1145\/3687272.3688320","type":"proceedings-article","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:24:28Z","timestamp":1732062268000},"page":"150-159","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["On the Effect of Robot Errors on Human Teaching Dynamics"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1512-2623","authenticated-orcid":false,"given":"Jindan","family":"Huang","sequence":"first","affiliation":[{"name":"Tufts University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4487-8357","authenticated-orcid":false,"given":"Isaac","family":"Sheidlower","sequence":"additional","affiliation":[{"name":"Tufts University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8615-3715","authenticated-orcid":false,"given":"Reuben M","family":"Aronson","sequence":"additional","affiliation":[{"name":"Tufts University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4789-9979","authenticated-orcid":false,"given":"Elaine Schaertl","family":"Short","sequence":"additional","affiliation":[{"name":"Tufts University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN50785.2021.9515510"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472307.3484184"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.23887\/jpai.v2i1.13736"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1111\/add.13501"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211041652"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2016.7745162"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157693"},{"key":"e_1_3_2_1_8_1","volume-title":"Open problems and fundamental limitations of reinforcement learning from human feedback. arXiv preprint arXiv:2307.15217","author":"Casper Stephen","year":"2023","unstructured":"Stephen Casper, Xander Davies, Claudia Shi, Thomas\u00a0Krendl Gilbert, J\u00e9r\u00e9my Scheurer, Javier Rando, Rachel Freedman, Tomasz Korbak, David Lindner, Pedro Freire, 2023. Open problems and fundamental limitations of reinforcement learning from human feedback. arXiv preprint arXiv:2307.15217 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN57019.2023.10309635"},{"key":"e_1_3_2_1_10_1","volume-title":"Deep reinforcement learning from human preferences. Advances in neural information processing systems 30","author":"Christiano F","year":"2017","unstructured":"Paul\u00a0F 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_1_11_1","volume-title":"Social Choice for AI Alignment: Dealing with Diverse Human Feedback. arXiv preprint arXiv:2404.10271","author":"Conitzer Vincent","year":"2024","unstructured":"Vincent Conitzer, Rachel Freedman, Jobst Heitzig, Wesley\u00a0H Holliday, Bob\u00a0M Jacobs, Nathan Lambert, Milan Moss\u00e9, Eric Pacuit, Stuart Russell, Hailey Schoelkopf, 2024. Social Choice for AI Alignment: Dealing with Diverse Human Feedback. arXiv preprint arXiv:2404.10271 (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489237"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/599"},{"key":"e_1_3_2_1_14_1","volume-title":"Safe rlhf: Safe reinforcement learning from human feedback. arXiv preprint arXiv:2310.12773","author":"Dai Josef","year":"2023","unstructured":"Josef Dai, Xuehai Pan, Ruiyang Sun, Jiaming Ji, Xinbo Xu, Mickel Liu, Yizhou Wang, and Yaodong Yang. 2023. Safe rlhf: Safe reinforcement learning from human feedback. arXiv preprint arXiv:2310.12773 (2023)."},{"key":"e_1_3_2_1_15_1","first-page":"235","article-title":"Modelling human teaching tactics and strategies for tutoring systems","volume":"12","author":"Du\u00a0Boulay Benedict","year":"2001","unstructured":"Benedict Du\u00a0Boulay and Rosemary Luckin. 2001. Modelling human teaching tactics and strategies for tutoring systems. International Journal of Artificial Intelligence in Education 12, 3 (2001), 235\u2013256.","journal-title":"International Journal of Artificial Intelligence in Education"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/tea.3660230904"},{"key":"e_1_3_2_1_17_1","volume-title":"Failure is an option: How the severity of robot errors affects human-robot interaction","author":"Gabriela\u00a0Morales Garza Cecilia","year":"2018","unstructured":"Cecilia Gabriela\u00a0Morales Garza. 2018. Failure is an option: How the severity of robot errors affects human-robot interaction. Pittsburgh: Carnegie Mellon University (2018)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25740"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610977.3634925"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.system.2006.09.001"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453154"},{"key":"e_1_3_2_1_22_1","first-page":"4415","article-title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","volume":"33","author":"Jeon Hong\u00a0Jun","year":"2020","unstructured":"Hong\u00a0Jun 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_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22362-4_31"},{"key":"e_1_3_2_1_24_1","volume-title":"A survey of reinforcement learning from human feedback. arXiv preprint arXiv:2312.14925","author":"Kaufmann Timo","year":"2023","unstructured":"Timo Kaufmann, Paul Weng, Viktor Bengs, and Eyke H\u00fcllermeier. 2023. A survey of reinforcement learning from human feedback. arXiv preprint arXiv:2312.14925 (2023)."},{"key":"e_1_3_2_1_25_1","first-page":"946","article-title":"The randomization theory of experimental inference","volume":"50","author":"Kempthorne Oscar","year":"1955","unstructured":"Oscar Kempthorne. 1955. The randomization theory of experimental inference. J. Amer. Statist. Assoc. 50, 271 (1955), 946\u2013967.","journal-title":"J. Amer. Statist. Assoc."},{"key":"e_1_3_2_1_26_1","unstructured":"Maurice\u00a0George Kendall. 1948. Rank correlation methods. (1948)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1514095.1514102"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319502.3374782"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Pallavi Koppol Henny Admoni and Reid\u00a0G Simmons. 2021. Interaction Considerations in Learning from Humans.. In IJCAI. 283\u2013291.","DOI":"10.24963\/ijcai.2021\/40"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3006254"},{"key":"e_1_3_2_1_31_1","volume-title":"Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning. arXiv preprint arXiv:2206.13316","author":"Lindner David","year":"2022","unstructured":"David Lindner and Mennatallah El-Assady. 2022. Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning. arXiv preprint arXiv:2206.13316 (2022)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8839"},{"key":"e_1_3_2_1_33_1","volume-title":"Rewarded by punishment: Reflections on the disuse of positive reinforcement in schools. Exceptional children 67, 2","author":"Maag W","year":"2001","unstructured":"John\u00a0W Maag. 2001. Rewarded by punishment: Reflections on the disuse of positive reinforcement in schools. Exceptional children 67, 2 (2001), 173\u2013186."},{"key":"e_1_3_2_1_34_1","volume-title":"Kruskal-wallis test. The corsini encyclopedia of psychology","author":"McKight E","year":"2010","unstructured":"Patrick\u00a0E McKight and Julius Najab. 2010. Kruskal-wallis test. The corsini encyclopedia of psychology (2010), 1\u20131."},{"key":"e_1_3_2_1_35_1","volume-title":"The Corsini encyclopedia of psychology","author":"McKnight E","year":"2010","unstructured":"Patrick\u00a0E McKnight and Julius Najab. 2010. Mann-Whitney U Test. The Corsini encyclopedia of psychology (2010), 1\u20131."},{"key":"e_1_3_2_1_36_1","volume-title":"RLHF-Blender: A Configurable Interactive Interface for Learning from Diverse Human Feedback. arXiv preprint arXiv:2308.04332","author":"Metz Yannick","year":"2023","unstructured":"Yannick Metz, David Lindner, Rapha\u00ebl Baur, Daniel Keim, and Mennatallah El-Assady. 2023. RLHF-Blender: A Configurable Interactive Interface for Learning from Diverse Human Feedback. arXiv preprint arXiv:2308.04332 (2023)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2017.00021"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10246-w"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3434074.3447183"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3434074.3447216"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbef.2017.12.004"},{"key":"e_1_3_2_1_42_1","volume-title":"Surf: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning. arXiv preprint arXiv:2203.10050","author":"Park Jongjin","year":"2022","unstructured":"Jongjin Park, Younggyo Seo, Jinwoo Shin, Honglak Lee, Pieter Abbeel, and Kimin Lee. 2022. Surf: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning. arXiv preprint arXiv:2203.10050 (2022)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.15348"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2696454.2696497"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611657"},{"key":"e_1_3_2_1_46_1","volume-title":"Temporal credit assignment in reinforcement learning","author":"Sutton Richard\u00a0Stuart","unstructured":"Richard\u00a0Stuart Sutton. 1984. Temporal credit assignment in reinforcement learning. University of Massachusetts Amherst."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.09.009"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2006.314459"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3439720"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-020-01798-5"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308532.3329475"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3380783"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920910802"},{"key":"e_1_3_2_1_54_1","volume-title":"Fresh: Interactive reward shaping in high-dimensional state spaces using human feedback. arXiv preprint arXiv:2001.06781","author":"Xiao Baicen","year":"2020","unstructured":"Baicen Xiao, Qifan Lu, Bhaskar Ramasubramanian, Andrew Clark, Linda Bushnell, and Radha Poovendran. 2020. Fresh: Interactive reward shaping in high-dimensional state spaces using human feedback. arXiv preprint arXiv:2001.06781 (2020)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN46459.2019.8956424"},{"key":"e_1_3_2_1_56_1","volume-title":"Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback. arXiv preprint arXiv:2402.02423","author":"Yuan Yifu","year":"2024","unstructured":"Yifu Yuan, Jianye Hao, Yi Ma, Zibin Dong, Hebin Liang, Jinyi Liu, Zhixin Feng, Kai Zhao, and Yan Zheng. 2024. Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback. arXiv preprint arXiv:2402.02423 (2024)."}],"event":{"name":"HAI '24: International Conference on Human-Agent Interaction","location":"Swansea United Kingdom","acronym":"HAI '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 12th International Conference on Human-Agent Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3687272.3688320","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3687272.3688320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:40:21Z","timestamp":1755866421000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3687272.3688320"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"references-count":56,"alternative-id":["10.1145\/3687272.3688320","10.1145\/3687272"],"URL":"https:\/\/doi.org\/10.1145\/3687272.3688320","relation":{},"subject":[],"published":{"date-parts":[[2024,11,24]]},"assertion":[{"value":"2024-11-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}