{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T17:44:47Z","timestamp":1776793487814,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":77,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T00:00:00Z","timestamp":1678665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["IIS-1924802, IIS-2106690"],"award-info":[{"award-number":["IIS-1924802, IIS-2106690"]}],"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":[[2023,3,13]]},"DOI":"10.1145\/3568162.3576986","type":"proceedings-article","created":{"date-parts":[[2023,3,9]],"date-time":"2023-03-09T18:08:48Z","timestamp":1678385328000},"page":"398-407","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Self-Annotation Methods for Aligning Implicit and Explicit Human Feedback in Human-Robot Interaction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8535-2771","authenticated-orcid":false,"given":"Qiping","family":"Zhang","sequence":"first","affiliation":[{"name":"Yale University, New Haven, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0320-5795","authenticated-orcid":false,"given":"Austin","family":"Narcomey","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0152-053X","authenticated-orcid":false,"given":"Kate","family":"Candon","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, CT, USA"}],"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, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,3,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319502.3374809"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21041292"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","unstructured":"Riku Arakawa Sosuke Kobayashi Yuya Unno Yuta Tsuboi and Shin-ichi Maeda. 2018. DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback. https:\/\/doi.org\/10.48550\/ARXIV.1810.11748","DOI":"10.48550\/ARXIV.1810.11748"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453445"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1017\/9781108676649"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136814"},{"key":"e_1_3_2_2_9_1","volume-title":"Artifical Intelligence for Human Computing, Thomas S","author":"Broekens Joost","unstructured":"Joost Broekens. 2007. Emotion and Reinforcement: Affective Facial Expressions Facilitate Robot Learning. In Artifical Intelligence for Human Computing, Thomas S. Huang, Anton Nijholt, Maja Pantic, and Alex Pentland (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 113--132."},{"key":"e_1_3_2_2_10_1","volume-title":"Proc. of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS '23)","author":"Candon Kate","year":"2023","unstructured":"Kate Candon, Zoe Hsu, Yoony Kim, Jesse Chen, Nathan Tsoi, and Marynel V\u00e1zquez. 2023. Nonverbal Human Signals Can Help Autonomous Agents Infer Human Preferences for Their Behavior. In Proc. of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS '23). IFAAMAS."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3576980"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843613500102"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-813445-0.00010-1"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2737019"},{"key":"e_1_3_2_2_16_1","volume-title":"Thomaz","author":"Chernova Sonia","year":"2014","unstructured":"Sonia Chernova and Andrea L. Thomaz. 2014. Robot Learning from Human Teachers. Morgan & Claypool Publishers."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794065"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319502.3374781"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/599"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i18.17998"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1037\/a0020019"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-017-0414-y"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3016387.3016461"},{"key":"e_1_3_2_2_25_1","volume-title":"Weinberger (Eds.)","volume":"26","author":"Griffith Shane","year":"2013","unstructured":"Shane Griffith, Kaushik Subramanian, Jonathan Scholz, Charles L Isbell, and Andrea L Thomaz. 2013. Policy Shaping: Integrating Human Feedback with Reinforcement Learning. In Advances in Neural Information Processing Systems, C.J. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger (Eds.), Vol. 26. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2013\/file\/ e034fb6b66aacc1d48f445ddfb08da98-Paper.pdf"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(08)62386-9"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1977.10480998"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1177\/1754073912451331"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1037\/0278-7393.10.4.598"},{"key":"e_1_3_2_2_30_1","volume-title":"Handbook of Linguistic Annotation","author":"Ide Nancy","unstructured":"Nancy Ide and James Pustejovsky. 2017. Handbook of Linguistic Annotation (1st ed.). Springer Publishing Company, Incorporated.","edition":"1"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/375735.376334"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2015.05.052"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Dinesh Babu Jayagopi Samira Sheikhi David Klotz Johannes Wienke Jean-Marc Odobez Sebastian Wrede Vasil Khalidov Laurent Nguyen Britta Wrede and Daniel Gatica-Perez. 2012. The Vernissage Corpus: A Multimodal Human-Robot-Interaction Dataset. (2012) 8. http:\/\/infoscience.epfl.ch\/record\/182715","DOI":"10.1109\/HRI.2013.6483545"},{"key":"e_1_3_2_2_34_1","volume-title":"Lin (Eds.)","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. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 4415--4426. https:\/\/proceedings. neurips.cc\/paper\/2020\/file\/2f10c1578a0706e06b6d7db6f0b4a6af-Paper.pdf"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2753767"},{"key":"e_1_3_2_2_36_1","volume-title":"Goffman's approach to face-to-face interaction. Erving Goffman: Exploring the interaction order","author":"Kendon Adam","year":"1988","unstructured":"Adam Kendon. 1988. Goffman's approach to face-to-face interaction. Erving Goffman: Exploring the interaction order (1988)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2909824.3020226"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-012-0163-x"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02675-6_46"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACII52823.2021.9597447"},{"key":"e_1_3_2_2_42_1","volume-title":"Jinjuan Heidi Feng, and Harry Hochheiser","author":"Lazar Jonathan","year":"2017","unstructured":"Jonathan Lazar, Jinjuan Heidi Feng, and Harry Hochheiser. 2017. Research methods in human-computer interaction. Morgan Kaufmann."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2696454.2696466"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-020-09447-w"},{"key":"e_1_3_2_2_45_1","volume-title":"Proceedings of the 2013 International Conference on Autonomous Agents and Multi-Agent Systems (St","author":"Li Guangliang","unstructured":"Guangliang Li, Hayley Hung, Shimon Whiteson, and W. Bradley Knox. 2013. Using Informative Behavior to Increase Engagement in the Tamer Framework. In Proceedings of the 2013 International Conference on Autonomous Agents and Multi-Agent Systems (St. Paul, MN, USA) (AAMAS '13). International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC, 909--916."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3006254"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9283-7"},{"key":"e_1_3_2_2_48_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations. https:\/\/openreview.net\/ forum?id=Bkg6RiCqY7","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In International Conference on Learning Representations. https:\/\/openreview.net\/ forum?id=Bkg6RiCqY7"},{"key":"e_1_3_2_2_49_1","volume-title":"International Conference on Machine Learning. PMLR, 2285--2294","author":"MacGlashan James","year":"2017","unstructured":"James MacGlashan, Mark K Ho, Robert Loftin, Bei Peng, Guan Wang, David L Roberts, Matthew E Taylor, and Michael L Littman. 2017. Interactive learning from policy-dependent human feedback. In International Conference on Machine Learning. PMLR, 2285--2294."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889395"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925434"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3522579"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2522865"},{"key":"e_1_3_2_2_54_1","volume-title":"Empathic Conversations: A Multi-level Dataset of Contextualized Conversations. arXiv preprint arXiv:2205.12698","author":"Omitaomu Damilola","year":"2022","unstructured":"Damilola Omitaomu, Shabnam Tafreshi, Tingting Liu, Sven Buechel, Chris Callison-Burch, Johannes Eichstaedt, Lyle Ungar, and Jo\u00e3o Sedoc. 2022. Empathic Conversations: A Multi-level Dataset of Contextualized Conversations. arXiv preprint arXiv:2205.12698 (2022)."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.528"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2011.5975338"},{"key":"e_1_3_2_2_57_1","volume-title":"ICRA Workshop on Open Source Software 3.","author":"Quigley Morgan","year":"2009","unstructured":"Morgan Quigley, Ken Conley, Brian Gerkey, Josh Faust, Tully Foote, Jeremy Leibs, Rob Wheeler, and Andrew Ng. 2009. ROS: an open-source Robot Operating System. ICRA Workshop on Open Source Software 3."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1037\/1528-3542.2.3.273"},{"key":"e_1_3_2_2_59_1","first-page":"99","article-title":"Comparison of multimodal annotation tools-workshop report","volume":"7","author":"Rohlfing Katharina","year":"2006","unstructured":"Katharina Rohlfing, Daniel Loehr, Susan Duncan, Amanda Brown, Amy Franklin, Irene Kimbara, Jan-Torsten Milde, Fey Parrill, Travis Rose, Thomas Schmidt, et al. 2006. Comparison of multimodal annotation tools-workshop report. Gespr\u00e4chforschung-Online-Zeitschrift zur Verbalen Interaktion 7 (2006), 99--123.","journal-title":"Gespr\u00e4chforschung-Online-Zeitschrift zur Verbalen Interaktion"},{"key":"e_1_3_2_2_60_1","volume-title":"Seshia","author":"Sadigh Dorsa","year":"2017","unstructured":"Dorsa Sadigh, Anca D. Dragan, S. Shankar Sastry, and Sanjit A. Seshia. 2017. Active Preference-Based Learning of Reward Functions. In Robotics: Science and Systems."},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.029"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2614525"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"e_1_3_2_2_64_1","volume-title":"Human Biases for Reward Inference. In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"5679","author":"Shah Rohin","year":"2019","unstructured":"Rohin Shah, Noah Gundotra, Pieter Abbeel, and Anca Dragan. 2019. On the Feasi-bility of Learning, Rather than Assuming, Human Biases for Reward Inference. In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhut-dinov (Eds.). PMLR, 5670--5679. https:\/\/proceedings.mlr.press\/v97\/shah19a.html"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981726"},{"key":"e_1_3_2_2_66_1","volume-title":"Generalized linear mixed models: modern concepts, methods and applications","author":"Stroup Walter W","unstructured":"Walter W Stroup. 2012. Generalized linear mixed models: modern concepts, methods and applications. CRC press."},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","unstructured":"Halit Bener Suay and Sonia Chernova. 2011. Effect of human guidance and state space size on Interactive Reinforcement Learning. In 2011 RO-MAN. 1--6. https:\/\/doi.org\/10.1109\/ROMAN.2011.6005223","DOI":"10.1109\/ROMAN.2011.6005223"},{"key":"e_1_3_2_2_68_1","volume-title":"Reinforcement learning: An intro- duction","author":"Sutton Richard S","unstructured":"Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An intro- duction. MIT press."},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.09.009"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636319"},{"key":"e_1_3_2_2_71_1","volume-title":"Understanding Social Behavior in Dyadic and Small Group Interactions (Proceedings of Machine Learning Research","volume":"293","author":"Quiros Jose Vargas","year":"2022","unstructured":"Jose Vargas Quiros, Stephanie Tan, Chirag Raman, Laura Cabrera-Quiros, and Hayley Hung. 2022. Covfee: an extensible web framework for continuous-time annotation of human behavior. In Understanding Social Behavior in Dyadic and Small Group Interactions (Proceedings of Machine Learning Research, Vol. 173), Cristina Palmero, Julio C. S. Jacques Junior, Albert Clap\u00e9s, Isabelle Guyon, Wei-Wei Tu, Thomas B. Moeslund, and Sergio Escalera (Eds.). PMLR, 265--293. https: \/\/proceedings.mlr.press\/v173\/vargas-quiros22a.html"},{"key":"e_1_3_2_2_72_1","volume-title":"Face valuing: Training user interfaces with facial expressions and reinforcement learning. arXiv preprint arXiv:1606.02807","author":"Veeriah Vivek","year":"2016","unstructured":"Vivek Veeriah, Patrick M Pilarski, and Richard S Sutton. 2016. Face valuing: Training user interfaces with facial expressions and reinforcement learning. arXiv preprint arXiv:1606.02807 (2016)."},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/2559636.2559684"},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02504798"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3242976"},{"key":"e_1_3_2_2_76_1","volume-title":"Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC'06)","author":"Wittenburg Peter","year":"2006","unstructured":"Peter Wittenburg, Hennie Brugman, Albert Russel, Alex Klassmann, and Han Sloetjes. 2006. ELAN: a Professional Framework for Multimodality Research. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC'06). European Language Resources Association (ELRA), Genoa, Italy. http:\/\/www.lrec-conf.org\/proceedings\/lrec2006\/pdf\/153_pdf.pdf"},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562098"}],"event":{"name":"HRI '23: ACM\/IEEE International Conference on Human-Robot Interaction","location":"Stockholm Sweden","acronym":"HRI '23","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2023 ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3568162.3576986","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3568162.3576986","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3568162.3576986","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:26:16Z","timestamp":1750281976000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3568162.3576986"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,13]]},"references-count":77,"alternative-id":["10.1145\/3568162.3576986","10.1145\/3568162"],"URL":"https:\/\/doi.org\/10.1145\/3568162.3576986","relation":{},"subject":[],"published":{"date-parts":[[2023,3,13]]},"assertion":[{"value":"2023-03-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}