{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T00:54:38Z","timestamp":1773536078926,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,16]]},"DOI":"10.1145\/3757279.3785583","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:27:38Z","timestamp":1773102458000},"page":"816-824","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Clarifying Constraints in Interactive Robot Learning with Language Feedback"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7778-4841","authenticated-orcid":false,"given":"Hannah","family":"Kuehn","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6924-4347","authenticated-orcid":false,"given":"Leonardo","family":"Santos","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2212-4325","authenticated-orcid":false,"given":"Iolanda","family":"Leite","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3466819"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3171221.3171267"},{"key":"e_1_3_2_2_4_1","volume-title":"Fitting linear mixed-effects models using lme4. 67","author":"Bates Douglas","year":"2015","unstructured":"Douglas Bates, Martin M\u00e4chler, Ben Bolker, and Steve Walker. 2015. Fitting linear mixed-effects models using lme4. 67 (2015), 1\u201348. https:\/\/www.jstatsoft.org\/article\/view\/v067i01\/0"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3576983"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","unstructured":"Anthony Brohan Noah Brown Justice Carbajal Yevgen Chebotar Xi Chen Krzysztof Choromanski Tianli Ding Danny Driess Avinava Dubey Chelsea Finn et al. 2023. RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control. In arXiv preprint arXiv:2307.15818. https:\/\/doi.org\/10.48550\/arXiv.2307.15818 10.48550\/arXiv.2307.15818","DOI":"10.48550\/arXiv.2307.15818"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3032845"},{"key":"e_1_3_2_2_8_1","volume-title":"Deep reinforcement learning from human preferences. 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. 30 (2017), https:\/\/proceedings.neurips.cc\/paper\/7017-deep-reinforcement-learning-from-"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-37703-7_18"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3578623"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1903.02020"},{"key":"e_1_3_2_2_13_1","first-page":"15281","article-title":"Unpacking Reward Shaping","volume":"35","author":"Gupta Abhishek","year":"2022","unstructured":"Abhishek Gupta, Aldo Pacchiano, Yuexiang Zhai, Sham Kakade, and Sergey Levine. 2022. Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity. 35 (2022), 15281\u201315295. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/hash\/6255f22349da5f2126dfc0b007075450-Abstract-Conference.html","journal-title":"Understanding the Benefits of Reward Engineering on Sample Complexity."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610977.3634970"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN63969.2025.11217743"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.04809"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.00001"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89350-9_6"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","unstructured":"Kimin Lee Laura Smith and Pieter Abbeel. 2021. PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training. arxiv:2106.05091 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2106.05091 10.48550\/arXiv.2106.05091","DOI":"10.48550\/arXiv.2106.05091"},{"key":"e_1_3_2_2_21_1","first-page":"2640","volume-title":"Proceedings of the 34th International Conference on Machine Learning. PMLR, 2285\u20132294","author":"MacGlashan James","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 Proceedings of the 34th International Conference on Machine Learning. PMLR, 2285\u20132294. https:\/\/proceedings.mlr.press\/v70\/macglashan17a.html ISSN: 2640-3498"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3128237"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","unstructured":"Austin Narcomey Nathan Tsoi Ruta Desai and Marynel V\u00e1zquez. 2024. Learning Human Preferences Over Robot Behavior as Soft Planning Constraints. arxiv:2403.19795 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2403.19795 10.48550\/arXiv.2403.19795","DOI":"10.48550\/arXiv.2403.19795"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","unstructured":"OpenAI : and Aaron Hurst et al. 2024. GPT-4o System Card. arxiv:2410.21276. https:\/\/doi.org\/10.48550\/arXiv.2410.21276 10.48550\/arXiv.2410.21276","DOI":"10.48550\/arXiv.2410.21276"},{"key":"e_1_3_2_2_25_1","unstructured":"Bharat Prakash Nicholas Waytowich Ashwinkumar Ganesan Tim Oates and Tinoosh Mohsenin. [n. d.]. Guiding Safe Reinforcement Learning Policies Using Structured Language Constraints."},{"key":"e_1_3_2_2_26_1","unstructured":"Bharat Prakash Nicholas R Waytowich Ashwinkumar Ganesan Tim Oates and Tinoosh Mohsenin. 2020. Guiding Safe Reinforcement Learning Policies Using Structured Language Constraints.. In SafeAI@ AAAI. 153\u2013161."},{"key":"e_1_3_2_2_27_1","article-title":"Open-Source Conversational AI with SpeechBrain 1.0","volume":"25","author":"Ravanelli Mirco","year":"2024","unstructured":"Mirco Ravanelli, Titouan Parcollet, Adel Moumen, Sylvain de Langen, Cem Subakan, Peter Plantinga, Yingzhi Wang, Pooneh Mousavi, Luca Della Libera, Artem Ploujnikov, Francesco Paissan, Davide Borra, Salah Zaiem, Zeyu Zhao, Shucong Zhang, Georgios Karakasidis, Sung-Lin Yeh, Pierre Champion, Aku Rouhe, Rudolf Braun, Florian Mai, Juan Zuluaga-Gomez, Seyed Mahed Mousavi, Andreas Nautsch, Ha Nguyen, Xuechen Liu, Sangeet Sagar, Jarod Duret, Salima Mdhaffar, Ga\u00eblle Laperri\u00e8re, Mickael Rouvier, Renato De Mori, and Yannick Est\u00e8ve. 2024. Open-Source Conversational AI with SpeechBrain 1.0. Journal of Machine Learning Research, 25, 333 (2024), http:\/\/jmlr.org\/papers\/v25\/24-0991.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","unstructured":"Pratyusha Sharma Balakumar Sundaralingam Valts Blukis Chris Paxton Tucker Hermans Antonio Torralba Jacob Andreas and Dieter Fox. 2022. Correcting Robot Plans with Natural Language Feedback. arxiv:2204.05186. https:\/\/doi.org\/10.48550\/arXiv.2204.05186 10.48550\/arXiv.2204.05186","DOI":"10.48550\/arXiv.2204.05186"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342290"},{"key":"e_1_3_2_2_30_1","unstructured":"Richard S Sutton Andrew G Barto et al. 1998. Reinforcement learning: An introduction. 1 MIT press Cambridge."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.17032"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889604"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3576966"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI61500.2025.10974241"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2309.11489"}],"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":[],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T00:31:32Z","timestamp":1773534692000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757279.3785583"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":35,"alternative-id":["10.1145\/3757279.3785583","10.1145\/3757279"],"URL":"https:\/\/doi.org\/10.1145\/3757279.3785583","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"}}]}}