{"id":"https://openalex.org/W7141380309","doi":"https://doi.org/10.1613/jair.1.19862","title":"Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance","display_name":"Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance","publication_year":2026,"publication_date":"2026-03-25","ids":{"openalex":"https://openalex.org/W7141380309","doi":"https://doi.org/10.1613/jair.1.19862"},"language":null,"primary_location":{"id":"doi:10.1613/jair.1.19862","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.19862","pdf_url":"https://jair.org/index.php/jair/article/download/19862/27286","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://jair.org/index.php/jair/article/download/19862/27286","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102912942","display_name":"Dimitris Michailidis","orcid":"https://orcid.org/0000-0002-0106-1126"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Dimitris Michailidis","raw_affiliation_strings":["a:1:{s:5:\"en_US\";s:23:\"University of Amsterdam\";}"],"affiliations":[{"raw_affiliation_string":"a:1:{s:5:\"en_US\";s:23:\"University of Amsterdam\";}","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130761288","display_name":"Willem R\u00f6pke","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Willem R\u00f6pke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081436755","display_name":"Diederik M. Roijers","orcid":"https://orcid.org/0000-0002-2825-2491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diederik M. Roijers","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009260617","display_name":"S. Ghebreab","orcid":"https://orcid.org/0009-0007-5788-4635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sennay Ghebreab","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130736309","display_name":"Fernando P. Santos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fernando P. Santos","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102912942"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.97276421,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"85","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.36899998784065247,"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":0.36899998784065247,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.18330000340938568,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.06239999830722809,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7998999953269958},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7493000030517578},{"id":"https://openalex.org/keywords/dominance","display_name":"Dominance (genetics)","score":0.6477000117301941},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5976999998092651},{"id":"https://openalex.org/keywords/fairness-measure","display_name":"Fairness measure","score":0.3497999906539917}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7998999953269958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914000153541565},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7493000030517578},{"id":"https://openalex.org/C151913843","wikidata":"https://www.wikidata.org/wiki/Q3454555","display_name":"Dominance (genetics)","level":3,"score":0.6477000117301941},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5976999998092651},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3926999866962433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3840000033378601},{"id":"https://openalex.org/C11867375","wikidata":"https://www.wikidata.org/wiki/Q5430671","display_name":"Fairness measure","level":4,"score":0.3497999906539917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34619998931884766},{"id":"https://openalex.org/C2986080485","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision maker","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2615000009536743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1613/jair.1.19862","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.19862","pdf_url":"https://jair.org/index.php/jair/article/download/19862/27286","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1613/jair.1.19862","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.19862","pdf_url":"https://jair.org/index.php/jair/article/download/19862/27286","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.7530366778373718}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7141380309.pdf","grobid_xml":"https://content.openalex.org/works/W7141380309.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-Objective":[0],"Reinforcement":[1],"Learning":[2],"(MORL)":[3],"aims":[4],"to":[5,66,74,85],"learn":[6],"a":[7,55,92],"set":[8],"of":[9,31,40,107],"policies":[10,76],"that":[11,58,101],"optimize":[12],"trade-offs":[13],"between":[14],"multiple,":[15],"often":[16],"conflicting":[17],"objectives.":[18],"MORL":[19,62],"is":[20],"computationally":[21],"more":[22],"complex":[23],"than":[24],"single-objective":[25],"RL,":[26],"particularly":[27,126],"as":[28],"the":[29,38,105],"number":[30],"objectives":[32,36],"increases.":[33],"Additionally,":[34],"when":[35],"involve":[37],"preferences":[39],"agents":[41],"or":[42],"groups,":[43],"incorporating":[44],"fairness":[45,60,88],"becomes":[46],"both":[47],"important":[48],"and":[49,81,99,118],"socially":[50],"desirable.":[51],"This":[52],"paper":[53],"introduces":[54],"principled":[56],"algorithm":[57],"incorporates":[59],"into":[61],"while":[63],"improving":[64],"scalability":[65,112],"many-objective":[67],"problems.":[68],"We":[69,90],"propose":[70],"using":[71],"Lorenz":[72],"dominance":[73,84],"identify":[75],"with":[77],"equitable":[78],"reward":[79],"distributions":[80],"introduce":[82],"\u03bb-Lorenz":[83],"enable":[86],"flexible":[87],"preferences.":[89],"release":[91],"new,":[93],"large-scale":[94],"real-world":[95],"transport":[96],"planning":[97],"environment":[98],"demonstrate":[100],"our":[102],"method":[103],"encourages":[104],"discovery":[106],"fair":[108],"policies,":[109],"showing":[110],"improved":[111],"in":[113,127],"two":[114],"large":[115],"cities":[116],"(Xi\u2019an":[117],"Amsterdam).":[119],"Our":[120],"methods":[121],"outperform":[122],"common":[123],"multi-objective":[124],"approaches,":[125],"high-dimensional":[128],"objective":[129],"spaces.":[130]},"counts_by_year":[],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2026-03-28T00:00:00"}