{"id":"https://openalex.org/W4410296827","doi":"https://doi.org/10.1109/hri61500.2025.10974226","title":"Bias and Performance Disparities in Reinforcement Learning for Human-Robot Interaction","display_name":"Bias and Performance Disparities in Reinforcement Learning for Human-Robot Interaction","publication_year":2025,"publication_date":"2025-03-04","ids":{"openalex":"https://openalex.org/W4410296827","doi":"https://doi.org/10.1109/hri61500.2025.10974226"},"language":"en","primary_location":{"id":"doi:10.1109/hri61500.2025.10974226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hri61500.2025.10974226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 20th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://kclpure.kcl.ac.uk/ws/files/320060974/hri2025_assistive_gym_audit.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117518467","display_name":"Zoe Evans","orcid":null},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zoe Evans","raw_affiliation_strings":["King's College London,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London,London,UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058021734","display_name":"Matteo Leonetti","orcid":"https://orcid.org/0000-0002-3831-2400"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matteo Leonetti","raw_affiliation_strings":["King's College London,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London,London,UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088379096","display_name":"Martim Brand\u00e3o","orcid":"https://orcid.org/0000-0002-2003-0675"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martim Brand\u00e3o","raw_affiliation_strings":["King's College London,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London,London,UK","institution_ids":["https://openalex.org/I183935753"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183935753"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04106023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1299","last_page":"1303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9463000297546387,"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":0.9463000297546387,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.909600019454956,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7240522503852844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6273530125617981},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.6179360151290894},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5558425784111023},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4526500701904297},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41833531856536865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.371143102645874},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15945231914520264},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.049491286277770996}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7240522503852844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6273530125617981},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.6179360151290894},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5558425784111023},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4526500701904297},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41833531856536865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.371143102645874},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15945231914520264},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.049491286277770996}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hri61500.2025.10974226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hri61500.2025.10974226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 20th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","raw_type":"proceedings-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/8611b6e3-911b-4bc2-a05d-f057779c681d","is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/8611b6e3-911b-4bc2-a05d-f057779c681d","pdf_url":"https://kclpure.kcl.ac.uk/ws/files/320060974/hri2025_assistive_gym_audit.pdf","source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Evans, Z, Leonetti, M & Brand\u00e3o, M 2025, Bias and Performance Disparities in Reinforcement Learning for Human-Robot Interaction. in 2025 ACM/IEEE International Conference on Human-Robot Interaction. https://doi.org/10.1109/HRI61500.2025.10974226","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/8611b6e3-911b-4bc2-a05d-f057779c681d","is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/8611b6e3-911b-4bc2-a05d-f057779c681d","pdf_url":"https://kclpure.kcl.ac.uk/ws/files/320060974/hri2025_assistive_gym_audit.pdf","source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Evans, Z, Leonetti, M & Brand\u00e3o, M 2025, Bias and Performance Disparities in Reinforcement Learning for Human-Robot Interaction. in 2025 ACM/IEEE International Conference on Human-Robot Interaction. https://doi.org/10.1109/HRI61500.2025.10974226","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410296827.pdf","grobid_xml":"https://content.openalex.org/works/W4410296827.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2978665606","https://openalex.org/W4287179229","https://openalex.org/W3205513966","https://openalex.org/W3120459843","https://openalex.org/W4366547574","https://openalex.org/W3200191727","https://openalex.org/W189465620","https://openalex.org/W4366818884","https://openalex.org/W2248308732","https://openalex.org/W4392651289"],"abstract_inverted_index":{"Bias":[0],"has":[1],"been":[2],"shown":[3],"to":[4,88,96,114],"be":[5],"a":[6,63,124],"pervasive":[7],"problem":[8],"in":[9,19,41,117],"machine":[10],"learning,":[11],"with":[12,49,77,123],"severe":[13],"and":[14,34,132,134],"unanticipated":[15],"consequences,":[16],"for":[17,45,70,119,136],"example":[18],"the":[20,50,54,112],"form":[21],"of":[22,52,126],"algorithm":[23],"performance":[24],"disparities":[25],"across":[26,75],"social":[27],"groups.":[28],"In":[29],"this":[30,83],"paper,":[31],"we":[32,66],"investigate":[33],"characterise":[35],"how":[36],"similar":[37],"issues":[38],"may":[39,101],"arise":[40,86],"Reinforcement":[42],"Learning":[43],"(RL)":[44],"Human-Robot":[46],"Interaction":[47],"(HRI),":[48],"intent":[51],"averting":[53],"same":[55],"ramifications.":[56],"Using":[57],"an":[58],"assistive":[59],"robotics":[60],"simulation":[61],"as":[62],"case":[64],"study,":[65],"show":[67,82],"that":[68,100],"RL":[69,118],"HRI":[71],"can":[72,85],"perform":[73],"differently":[74],"models":[76],"different":[78],"waist":[79],"circumferences.":[80],"We":[81,121],"behaviour":[84],"due":[87,95],"representation":[89],"bias-unbalanced":[90],"exposure":[91],"during":[92],"training-but":[93],"also":[94],"inherent":[97],"task":[98],"properties":[99],"make":[102],"assistance":[103],"difficult":[104],"depending":[105],"on":[106],"physical":[107],"characteristics.":[108],"The":[109],"findings":[110],"underscore":[111],"need":[113],"address":[115],"bias":[116],"HRI.":[120],"conclude":[122],"discussion":[125],"potential":[127],"practical":[128],"solutions,":[129],"their":[130],"consequences":[131],"limitations,":[133],"avenues":[135],"future":[137],"research.":[138]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}