{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T15:34:58Z","timestamp":1776094498290,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":91,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T00:00:00Z","timestamp":1710720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","award":["InnoHK funding"],"award-info":[{"award-number":["InnoHK funding"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"HKUST & HKPC Joint Laboratory","award":["HKPC22EG01-A"],"award-info":[{"award-number":["HKPC22EG01-A"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,18]]},"DOI":"10.1145\/3640543.3645145","type":"proceedings-article","created":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T18:23:12Z","timestamp":1712341392000},"page":"344-369","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["FARPLS: A Feature-Augmented Robot Trajectory Preference Labeling System to Assist Human Labelers\u2019 Preference Elicitation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0135-5754","authenticated-orcid":false,"given":"Hanfang","family":"Lyu","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2140-7894","authenticated-orcid":false,"given":"Yuanchen","family":"Bai","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1497-4404","authenticated-orcid":false,"given":"Xin","family":"Liang","sequence":"additional","affiliation":[{"name":"Tongji University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6852-3938","authenticated-orcid":false,"given":"Ujaan","family":"Das","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3370-1626","authenticated-orcid":false,"given":"Chuhan","family":"Shi","sequence":"additional","affiliation":[{"name":"Southeast University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4302-1592","authenticated-orcid":false,"given":"Leiliang","family":"Gong","sequence":"additional","affiliation":[{"name":"Robotics and AI Division, Hong Kong Productivity Council, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9457-4303","authenticated-orcid":false,"given":"Yingchi","family":"Li","sequence":"additional","affiliation":[{"name":"Hong Kong Industrial Artificial Intelligence and Robotics Centre (FLAIR), China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5925-5425","authenticated-orcid":false,"given":"Mingfei","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Manchester, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2768-1374","authenticated-orcid":false,"given":"Ming","family":"Ge","sequence":"additional","affiliation":[{"name":"Robotics and Artificial Intelligence Division, Hong Kong Productivity Council, China and Hong Kong Industrial Artificial Intelligence and Robotics Centre (FLAIR), China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9847-7784","authenticated-orcid":false,"given":"Xiaojuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2024,4,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Josh Abramson Arun Ahuja Federico Carnevale Petko Georgiev Alex Goldin Alden Hung Jessica Landon Jirka Lhotka Timothy Lillicrap Alistair Muldal George Powell Adam Santoro Guy Scully Sanjana Srivastava Tamara von Glehn Greg Wayne Nathaniel Wong Chen Yan and Rui Zhu. 2022. Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback. https:\/\/doi.org\/10.48550\/arXiv.2211.11602 arxiv:2211.11602\u00a0[cs]","DOI":"10.48550\/arXiv.2211.11602"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of 2002 AAAI Fall Symposium. AAAI Press","author":"Adams A","year":"2002","unstructured":"Julie\u00a0A Adams. 2002. Critical considerations for human-robot interface development. In Proceedings of 2002 AAAI Fall Symposium. AAAI Press, North Falmouth, Massachusetts, USA, 1\u20138."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33486-3_8"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3434073.3444651"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the Conference on Robot Learning. PMLR, Virtual, 1177\u20131190","author":"B\u0131y\u0131k Erdem","year":"2020","unstructured":"Erdem B\u0131y\u0131k, Malayandi Palan, Nicholas\u00a0C. Landolfi, Dylan\u00a0P. Losey, and Dorsa Sadigh. 2020. Asking Easy Questions: A User-Friendly Approach to Active Reward Learning. In Proceedings of the Conference on Robot Learning. PMLR, Virtual, 1177\u20131190."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","unstructured":"Andreea Bobu Andi Peng Pulkit Agrawal Julie Shah and Anca\u00a0D. Dragan. 2023. Aligning Robot and Human Representations. https:\/\/doi.org\/10.48550\/arxiv.2302.01928 arxiv:2302.01928\u00a0[cs]","DOI":"10.48550\/arxiv.2302.01928"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3434073.3444667"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525047"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a097)","author":"Brown Daniel","year":"2019","unstructured":"Daniel Brown, Wonjoon Goo, Prabhat Nagarajan, and Scott Niekum. 2019. Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations. In Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a097), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, Long Beach, California, USA, 783\u2013792. https:\/\/proceedings.mlr.press\/v97\/brown19a.html"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557253"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1216295.1216317"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78646-7_5"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Stephen Casper Xander Davies Claudia Shi Thomas\u00a0Krendl Gilbert J\u00e9r\u00e9my Scheurer Javier Rando Rachel Freedman Tomasz Korbak David Lindner Pedro Freire Tony Wang Samuel Marks Charbel-Rapha\u00ebl Segerie Micah Carroll Andi Peng Phillip Christoffersen Mehul Damani Stewart Slocum Usman Anwar Anand Siththaranjan Max Nadeau Eric\u00a0J. Michaud Jacob Pfau Dmitrii Krasheninnikov Xin Chen Lauro Langosco Peter Hase Erdem B\u0131y\u0131k Anca Dragan David Krueger Dorsa Sadigh and Dylan Hadfield-Menell. 2023. Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback. https:\/\/doi.org\/10.48550\/arXiv.2307.15217 arxiv:2307.15217\u00a0[cs]","DOI":"10.48550\/arXiv.2307.15217"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of The 6th Conference on Robot Learning. PMLR","author":"Chandan Kishan\u00a0Dhananjay","year":"2022","unstructured":"Kishan\u00a0Dhananjay Chandan, Jack Albertson, and Shiqi Zhang. 2022. Learning Visualization Policies of Augmented Reality for Human-Robot Collaboration. In Proceedings of The 6th Conference on Robot Learning. PMLR, Auckland, New Zealand, 1233\u20131243."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.905819"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300460"},{"key":"e_1_3_2_1_18_1","volume-title":"Advances in Neural Information Processing Systems, I.\u00a0Guyon, U.\u00a0Von Luxburg, S.\u00a0Bengio, H.\u00a0Wallach, R.\u00a0Fergus, S.\u00a0Vishwanathan, and R.\u00a0Garnett (Eds.). Vol.\u00a030. Curran Associates","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. In Advances in Neural Information Processing Systems, I.\u00a0Guyon, U.\u00a0Von Luxburg, S.\u00a0Bengio, H.\u00a0Wallach, R.\u00a0Fergus, S.\u00a0Vishwanathan, and R.\u00a0Garnett (Eds.). Vol.\u00a030. Curran Associates, Inc., Long Beach, California, USA. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/d5e2c0adad503c91f91df240d0cd4e49-Paper.pdf"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1979.10481038"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329204"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.05.174"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1240624.1240684"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.12945\/j.aorta.2016.16.014"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2019.2938316"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/robotics11010029"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2013.6483603"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v9i1.18939"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350535"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979116"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-64148-1_13"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3119930"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13667"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jspi.2003.09.022"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the Conference on Robot Learning(Proceedings of Machine Learning Research, Vol.\u00a0100)","author":"Gupta Abhishek","year":"2020","unstructured":"Abhishek Gupta, Vikash Kumar, Corey Lynch, Sergey Levine, and Karol Hausman. 2020. Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning. In Proceedings of the Conference on Robot Learning(Proceedings of Machine Learning Research, Vol.\u00a0100), Leslie\u00a0Pack Kaelbling, Danica Kragic, and Komei Sugiura (Eds.). PMLR, Virtual, 1025\u20131037. https:\/\/proceedings.mlr.press\/v100\/gupta20a.html"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526107"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1177\/09567976211032887"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"e_1_3_2_1_38_1","unstructured":"Rachel Holladay Shervin Javdani Anca Dragan and Siddhartha Srinivasa. 2016. Active Comparison Based Learning Incorporating User Uncertainty and Noise."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2008.08.002"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2008.08.002"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-4870(88)90051-7"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517457"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-3758(97)00131-6"},{"key":"e_1_3_2_1_44_1","volume-title":"Unskilled and unaware of it: how difficulties in recognizing one\u2019s own incompetence lead to inflated self-assessments.Journal of personality and social psychology 77, 6","author":"Kruger Justin","year":"1999","unstructured":"Justin Kruger and David Dunning. 1999. Unskilled and unaware of it: how difficulties in recognizing one\u2019s own incompetence lead to inflated self-assessments.Journal of personality and social psychology 77, 6 (1999), 1121."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132169"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300742"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889458"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00436"},{"key":"e_1_3_2_1_49_1","unstructured":"Zihao Li Zhuoran Yang and Mengdi Wang. 2023. Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism. arxiv:2305.18438\u00a0[cs.LG]"},{"key":"e_1_3_2_1_50_1","unstructured":"Gabrielle Kaili-May Liu. 2023. Perspectives on the Social Impacts of Reinforcement Learning with Human Feedback. arXiv preprint. https:\/\/arxiv.org\/abs\/2303.02891 arXiv preprint arXiv:2303.02891."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMSC.2017.7959506"},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the 5th Conference on Robot Learning(Proceedings of Machine Learning Research, Vol.\u00a0164)","author":"Mandlekar Ajay","year":"2022","unstructured":"Ajay Mandlekar, Danfei Xu, Josiah Wong, Soroush Nasiriany, Chen Wang, Rohun Kulkarni, Li Fei-Fei, Silvio Savarese, Yuke Zhu, and Roberto Mart\u00edn-Mart\u00edn. 2022. What Matters in Learning from Offline Human Demonstrations for Robot Manipulation. In Proceedings of the 5th Conference on Robot Learning(Proceedings of Machine Learning Research, Vol.\u00a0164), Aleksandra Faust, David Hsu, and Gerhard Neumann (Eds.). PMLR, London, UK, 1678\u20131690. https:\/\/proceedings.mlr.press\/v164\/mandlekar22a.html"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730491"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242671.3242710"},{"key":"e_1_3_2_1_55_1","unstructured":"Microsoft. 2021. VoTT. https:\/\/github.com\/microsoft\/VoTT."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501842"},{"key":"e_1_3_2_1_57_1","volume-title":"Foundations of machine learning","author":"Mohri Mehryar","unstructured":"Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar. 2018. Foundations of machine learning. MIT press, Cambridge, MA."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581184"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/1957656.1957786"},{"key":"e_1_3_2_1_60_1","volume-title":"Proceedings of the 5th Conference on Robot Learning(Proceedings of Machine Learning Research, Vol.\u00a0164)","author":"Myers Vivek","year":"2022","unstructured":"Vivek Myers, Erdem Biyik, Nima Anari, and Dorsa Sadigh. 2022. Learning Multimodal Rewards from Rankings. In Proceedings of the 5th Conference on Robot Learning(Proceedings of Machine Learning Research, Vol.\u00a0164), Aleksandra Faust, David Hsu, and Gerhard Neumann (Eds.). PMLR, London, UK, 342\u2013352. https:\/\/proceedings.mlr.press\/v164\/myers22a.html"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3576965"},{"key":"e_1_3_2_1_62_1","volume-title":"Advances in Neural Information Processing Systems, S.\u00a0Koyejo, S.\u00a0Mohamed, A.\u00a0Agarwal, D.\u00a0Belgrave, K.\u00a0Cho, and A.\u00a0Oh (Eds.). Vol.\u00a035. Curran Associates","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul\u00a0F Christiano, Jan Leike, and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems, S.\u00a0Koyejo, S.\u00a0Mohamed, A.\u00a0Agarwal, D.\u00a0Belgrave, K.\u00a0Cho, and A.\u00a0Oh (Eds.). Vol.\u00a035. Curran Associates, Inc., New Orleans, LA, USA [hybrid], 27730\u201327744. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/b1efde53be364a73914f58805a001731-Paper-Conference.pdf"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.14778\/2809974.2809992"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316782.3316791"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2010.66"},{"key":"e_1_3_2_1_66_1","volume-title":"KDD workshop on mining temporal and sequential data, Vol.\u00a06","author":"Salvador Stan","year":"2004","unstructured":"Stan Salvador and Philip Chan. 2004. FastDTW: Toward accurate dynamic time warping in linear time and space. In KDD workshop on mining temporal and sequential data, Vol.\u00a06. Seattle, Washington, Association for Computing Machinery, New York, NY, USA, 70\u201380."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.5555\/3523760.3523770"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568294.3580147"},{"key":"e_1_3_2_1_69_1","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP \u201911)","author":"Settles Burr","year":"2011","unstructured":"Burr Settles. 2011. Closing the Loop: Fast, Interactive Semi-Supervised Annotation with Queries on Features and Instances. In Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP \u201911). Association for Computational Linguistics, USA, 1467\u20131478."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3429448"},{"key":"e_1_3_2_1_71_1","unstructured":"Daniel Shin Anca Dragan and Daniel\u00a0S. Brown. 2023. Benchmarks and Algorithms for Offline Preference-Based Reward Learning. https:\/\/openreview.net\/forum?id=TGuXXlbKsn"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.intcom.2007.02.002"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3434073.3444683"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/BioRob.2012.6290666"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450668"},{"key":"e_1_3_2_1_76_1","volume-title":"Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems (Hamburg Germany","author":"Wang Chao","unstructured":"Chao Wang, Joerg Deigmoeller, Pengcheng An, and Julian Eggert. [n. d.]. A User Interface for Sense-making of the Reasoning Process While Interacting with Robots. In Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems (Hamburg Germany, 2023-04-19). ACM, 1\u20137. https:\/\/doi.org\/10\/gss3j7"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581127"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1002\/cfp2.1032"},{"key":"e_1_3_2_1_79_1","volume-title":"Proceedings of the 5th Conference on Robot Learning(Proceedings of Machine Learning Research, Vol.\u00a0164)","author":"Wilde Nils","year":"2022","unstructured":"Nils Wilde, Erdem B\u0131y\u0131k, Dorsa Sadigh, and Stephen\u00a0L. Smith. 2022. Learning Reward Functions from Scale Feedback. In Proceedings of the 5th Conference on Robot Learning(Proceedings of Machine Learning Research, Vol.\u00a0164), Aleksandra Faust, David Hsu, and Gerhard Neumann (Eds.). PMLR, London, UK, 353\u2013362. https:\/\/proceedings.mlr.press\/v164\/wilde22a.html"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1002\/wics.46"},{"key":"e_1_3_2_1_81_1","volume-title":"Proceedings of the 3rd Machine Learning for Healthcare Conference(Proceedings of Machine Learning Research, Vol.\u00a085)","author":"Woodworth Bryce","year":"2018","unstructured":"Bryce Woodworth, Francesco Ferrari, Teofilo\u00a0E. Zosa, and Laurel\u00a0D. Riek. 2018. Preference Learning in Assistive Robotics: Observational Repeated Inverse Reinforcement Learning. In Proceedings of the 3rd Machine Learning for Healthcare Conference(Proceedings of Machine Learning Research, Vol.\u00a085), Finale Doshi-Velez, Jim Fackler, Ken Jung, David Kale, Rajesh Ranganath, Byron Wallace, and Jenna Wiens (Eds.). PMLR, Palo Alto, California, USA, 420\u2013439. https:\/\/proceedings.mlr.press\/v85\/woodworth18a.html"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1988.194289"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm4183"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3063927"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3576986"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3412848"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517612"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmapro.2020.05.004"},{"key":"e_1_3_2_1_89_1","volume-title":"ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation Models. OpenReview.net, Online + Kigali, Rwanda. https:\/\/openreview.net\/forum?id=pm_WNYd7SP","author":"Zhu Banghua","year":"2023","unstructured":"Banghua Zhu, Jiantao Jiao, and Michael Jordan. 2023. Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons. In ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation Models. OpenReview.net, Online + Kigali, Rwanda. https:\/\/openreview.net\/forum?id=pm_WNYd7SP"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68792-6_38"},{"key":"e_1_3_2_1_91_1","volume-title":"Robosuite: A Modular Simulation Framework and Benchmark for Robot Learning. arxiv:2009.12293","author":"Zhu Yuke","year":"2020","unstructured":"Yuke Zhu, Josiah Wong, Ajay Mandlekar, and Roberto Mart\u00edn-Mart\u00edn. 2020. Robosuite: A Modular Simulation Framework and Benchmark for Robot Learning. arxiv:2009.12293"}],"event":{"name":"IUI '24: 29th International Conference on Intelligent User Interfaces","location":"Greenville SC USA","acronym":"IUI '24","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 29th International Conference on Intelligent User Interfaces"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640543.3645145","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640543.3645145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:56:36Z","timestamp":1764550596000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640543.3645145"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,18]]},"references-count":91,"alternative-id":["10.1145\/3640543.3645145","10.1145\/3640543"],"URL":"https:\/\/doi.org\/10.1145\/3640543.3645145","relation":{},"subject":[],"published":{"date-parts":[[2024,3,18]]},"assertion":[{"value":"2024-04-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}