{"id":"https://openalex.org/W7135036548","doi":"https://doi.org/10.1145/3776734.3794500","title":"First Impressions Matter: Primacy Bias in Deep Reinforcement Learning during Human-Robot Co-learning","display_name":"First Impressions Matter: Primacy Bias in Deep Reinforcement Learning during Human-Robot Co-learning","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135036548","doi":"https://doi.org/10.1145/3776734.3794500"},"language":null,"primary_location":{"id":"doi:10.1145/3776734.3794500","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776734.3794500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090222528","display_name":"Christos Spatharis","orcid":"https://orcid.org/0009-0001-2791-2291"},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Christos Spatharis","raw_affiliation_strings":["National Centre for Scientific Research \u2018Demokritos\u2019, Ag. Paraskevi, Greece"],"raw_orcid":"https://orcid.org/0009-0001-2791-2291","affiliations":[{"raw_affiliation_string":"National Centre for Scientific Research \u2018Demokritos\u2019, Ag. Paraskevi, Greece","institution_ids":["https://openalex.org/I203474044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052859018","display_name":"Dimitrios Koutrintzes","orcid":null},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitrios Koutrintzes","raw_affiliation_strings":["National Centre for Scientific Research \u2018Demokritos\u2019, Ag. Paraskevi, Greece"],"raw_orcid":"https://orcid.org/0009-0003-7401-6347","affiliations":[{"raw_affiliation_string":"National Centre for Scientific Research \u2018Demokritos\u2019, Ag. Paraskevi, Greece","institution_ids":["https://openalex.org/I203474044"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031672975","display_name":"Maria Dagioglou","orcid":"https://orcid.org/0000-0002-3357-2844"},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Maria Dagioglou","raw_affiliation_strings":["National Centre for Scientific Research \u2018Demokritos\u2019, Ag. Paraskevi, Greece"],"raw_orcid":"https://orcid.org/0000-0002-3357-2844","affiliations":[{"raw_affiliation_string":"National Centre for Scientific Research \u2018Demokritos\u2019, Ag. Paraskevi, Greece","institution_ids":["https://openalex.org/I203474044"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I203474044"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29505055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"773","last_page":"777"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.39800000190734863,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.39800000190734863,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.17649999260902405,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.08139999955892563,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.35989999771118164},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3183000087738037},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.26980000734329224},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.267300009727478},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.2621000111103058}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.6169000267982483},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5002999901771545},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.38519999384880066},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29190000891685486},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.260699987411499},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3776734.3794500","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776734.3794500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4199584424495697,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W3115959388","https://openalex.org/W3132954338","https://openalex.org/W3178075461","https://openalex.org/W3180483112","https://openalex.org/W3206921000","https://openalex.org/W4280502627","https://openalex.org/W4297518097","https://openalex.org/W4397026139","https://openalex.org/W4399146400","https://openalex.org/W4400839876","https://openalex.org/W4401416451","https://openalex.org/W4401417103","https://openalex.org/W4401793915","https://openalex.org/W6930644721"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,66,86],"enables":[3],"robots":[4],"to":[5,21,23,54,84,93],"learn":[6],"collaborative":[7],"tasks":[8],"with":[9,49],"humans.":[10],"However,":[11],"off-policy":[12],"methods":[13],"suffer":[14],"from":[15],"primacy":[16,31],"bias":[17,32],"that":[18,69,98],"causes":[19],"agents":[20],"overfit":[22],"early":[24,80],"experiences.":[25],"We":[26],"investigate":[27],"the":[28,70,73,91],"impact":[29],"of":[30,60,72],"on":[33],"team":[34],"performance":[35],"during":[36],"a":[37,50,56],"real":[38],"world":[39],"human-robot":[40],"co-learning":[41],"task,":[42],"where":[43],"twenty":[44],"novice":[45],"human":[46,103],"participants":[47],"collaborated":[48],"Soft":[51],"Actor-Critic":[52],"agent":[53,92],"move":[55],"UR3":[57],"cobot.":[58],"Analysis":[59],"how":[61],"initial":[62,74],"interactions":[63,89],"shape":[64],"subsequent":[65],"dynamics":[67],"demonstrates":[68],"quality":[71],"data":[75],"distribution":[76],"matters.":[77],"While":[78],"successful":[79],"experiences":[81],"allow":[82],"teams":[83],"overcome":[85],"barriers,":[87],"poor":[88],"cause":[90],"converge":[94],"toward":[95],"suboptimal":[96],"behaviors":[97],"prevent":[99],"recovery,":[100],"even":[101],"as":[102],"skills":[104],"improve.":[105]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-03-13T00:00:00"}
