{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:33:30Z","timestamp":1773376410491,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","funder":[{"name":"European High-Performance computing Joint Undertaking \\\/ Greek Ministry of Digital Governance","award":["101234269"],"award-info":[{"award-number":["101234269"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,16]]},"DOI":"10.1145\/3776734.3794500","type":"proceedings-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:05:48Z","timestamp":1773345948000},"page":"773-777","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["First Impressions Matter: Primacy Bias in Deep Reinforcement Learning during Human-Robot Co-learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2791-2291","authenticated-orcid":false,"given":"Christos","family":"Spatharis","sequence":"first","affiliation":[{"name":"National Centre for Scientific Research \u2018Demokritos\u2019, Ag. Paraskevi, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7401-6347","authenticated-orcid":false,"given":"Dimitrios","family":"Koutrintzes","sequence":"additional","affiliation":[{"name":"National Centre for Scientific Research \u2018Demokritos\u2019, Ag. Paraskevi, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3357-2844","authenticated-orcid":false,"given":"Maria","family":"Dagioglou","sequence":"additional","affiliation":[{"name":"National Centre for Scientific Research \u2018Demokritos\u2019, Ag. Paraskevi, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Zeyuan Cai Zhiquan Feng Liran Zhou Changsheng Ai Haiyan Shao and Xiaohui Yang. 2022. A Framework and Algorithm for Human-Robot Collaboration Based on Multimodal Reinforcement Learning. Computational Intelligence and Neuroscience https:\/\/doi.org\/10.1155\/2022\/2341898 10.1155\/2022\/2341898","DOI":"10.1155\/2022\/2341898"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610694"},{"key":"e_1_3_2_1_3_1","unstructured":"Petros Christodoulou. 2019. Soft actor-critic for discrete action settings. arXiv preprint arXiv:1910.07207."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07711-7"},{"key":"e_1_3_2_1_5_1","unstructured":"Massimiliano Falzari and Matthia Sabatelli. 2025. Mitigating The Primacy Bias in Deep Reinforcement Learning. arXiv."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3047730"},{"key":"e_1_3_2_1_7_1","volume-title":"International conference on machine learning. 1861\u20131870","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning. 1861\u20131870."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3403709"},{"key":"e_1_3_2_1_9_1","first-page":"995","article-title":"Dissecting Deep RL with High Update Ratios: Combatting Value Divergence","volume":"2","author":"Hussing Marcel","year":"2024","unstructured":"Marcel Hussing, Claas Voelcker, Igor Gilitschenski, Amir massoud Farahmand, and Eric Eaton. 2024. Dissecting Deep RL with High Update Ratios: Combatting Value Divergence. Reinforcement Learing Journal, 2 (2024), 995\u20131018.","journal-title":"Reinforcement Learing Journal"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.14772018"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3397704"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453892.3454004"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610595"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.07802"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1101\/2024.07.15.603502"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102432"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341473"},{"key":"e_1_3_2_1_18_1","unstructured":"Athanasios C Tsitos and Maria Dagioglou. 2022. Enhancing team performance with transfer-learning during real-world human-robot collaboration. arXiv preprint arXiv:2211.13070."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.692811"}],"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":["Companion Proceedings of the 21st ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:13:30Z","timestamp":1773346410000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3776734.3794500"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":19,"alternative-id":["10.1145\/3776734.3794500","10.1145\/3776734"],"URL":"https:\/\/doi.org\/10.1145\/3776734.3794500","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"}}]}}