{"id":"https://openalex.org/W7128722671","doi":"https://doi.org/10.48448/41s9-9587","title":"1346 - Fairness Aware Reinforcement Learning via Proximal Policy Optimization","display_name":"1346 - Fairness Aware Reinforcement Learning via Proximal Policy Optimization","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7128722671","doi":"https://doi.org/10.48448/41s9-9587"},"language":"en","primary_location":{"id":"doi:10.48448/41s9-9587","doi":"https://doi.org/10.48448/41s9-9587","is_oa":true,"landing_page_url":"https://doi.org/10.48448/41s9-9587","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"volume":null,"type":"other","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/41s9-9587","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125741655","display_name":"Association for Artificial Intelligence 2026","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Artificial Intelligence 2026","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021351903","display_name":"Elizabeth Black","orcid":"https://orcid.org/0000-0002-4295-449X","observed_orcids":["https://orcid.org/0000-0002-4295-449X"]},"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":"Black, Elizabeth","raw_affiliation_strings":["King's College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114337724","display_name":"Gabriele La Malfa","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"la Malfa, Gabriele","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135926240","display_name":"Michael Luck","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luck, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088708850","display_name":"Jie M. Zhang","orcid":"https://orcid.org/0000-0003-0481-7264","observed_orcids":["https://orcid.org/0000-0003-0481-7264","https://orcid.org/0000-0001-7733-5392"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"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":0.7455999851226807,"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":0.7455999851226807,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.24320000410079956,"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/T10991","display_name":"Game Theory and Voting Systems","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.8379999995231628},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.9570000171661377},{"id":"https://openalex.org/keywords/demographic-parity","display_name":"demographic parity","score":0.8360000252723694},{"id":"https://openalex.org/keywords/counterfactual-fairness","display_name":"counterfactual fairness","score":0.9900000095367432},{"id":"https://openalex.org/keywords/sensitive-attributes","display_name":"sensitive attributes","score":0.8429999947547913},{"id":"https://openalex.org/keywords/hospital-simulation","display_name":"hospital simulation","score":0.49799999594688416},{"id":"https://openalex.org/keywords/gini-coefficient","display_name":"Gini coefficient","score":0.6430000066757202}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8062999844551086},{"id":"https://openalex.org/C11867375","wikidata":"https://www.wikidata.org/wiki/Q5430671","display_name":"Fairness measure","level":4,"score":0.7085999846458435},{"id":"https://openalex.org/C177972170","wikidata":"https://www.wikidata.org/wiki/Q17097315","display_name":"Max-min fairness","level":3,"score":0.6279000043869019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6172000169754028},{"id":"https://openalex.org/C46355384","wikidata":"https://www.wikidata.org/wiki/Q726686","display_name":"Compromise","level":2,"score":0.5049999952316284},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.35370001196861267},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.33469998836517334},{"id":"https://openalex.org/C147077947","wikidata":"https://www.wikidata.org/wiki/Q1515895","display_name":"Socioeconomic status","level":3,"score":0.3310999870300293},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3021000027656555},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2842999994754791},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C100001284","wikidata":"https://www.wikidata.org/wiki/Q2248246","display_name":"Public economics","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.26820001006126404},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.25200000405311584},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/41s9-9587","doi":"https://doi.org/10.48448/41s9-9587","is_oa":true,"landing_page_url":"https://doi.org/10.48448/41s9-9587","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/41s9-9587","doi":"https://doi.org/10.48448/41s9-9587","is_oa":true,"landing_page_url":"https://doi.org/10.48448/41s9-9587","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.8974000215530396,"id":"https://metadata.un.org/sdg/10"},{"display_name":"Peace, justice, and strong institutions","score":0.5473999977111816,"id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7128738615","https://openalex.org/W4379255986","https://openalex.org/W7124291675","https://openalex.org/W7136911572","https://openalex.org/W2970727184","https://openalex.org/W7106135513","https://openalex.org/W3167120022","https://openalex.org/W7124126629","https://openalex.org/W7164563769","https://openalex.org/W6891707180"],"abstract_inverted_index":{"Fairness":[0,178],"in":[1,12,28,75,85,92,119,208],"multi-agent":[2],"systems":[3],"(MAS)":[4],"focuses":[5],"on":[6,104],"equitable":[7],"reward":[8,60],"distribution":[9],"among":[10,191],"agents":[11,109,121],"scenarios":[13],"involving":[14],"sensitive":[15,112],"attributes":[16],"such":[17,42],"as":[18,43],"race,":[19],"gender,":[20],"or":[21,48],"socioeconomic":[22],"status.":[23],"This":[24],"paper":[25],"introduces":[26],"fairness":[27,40,63,84,145,206],"Proximal":[29],"Policy":[30],"Optimization":[31],"(PPO)":[32],"with":[33,62,128,171],"a":[34,39,69,79,98,111,116,156],"penalty":[35,67,153],"term":[36],"derived":[37],"from":[38],"definition":[41],"demographic":[44],"parity,":[45],"counterfactual":[46],"fairness,":[47],"conditional":[49],"statistical":[50],"parity.":[51],"The":[52],"proposed":[53],"method,":[54],"which":[55,120],"we":[56],"call":[57],"Fair-PPO,":[58],"balances":[59],"maximisation":[61],"by":[64],"integrating":[65],"two":[66,93],"components:":[68],"retrospective":[70,150],"component":[71,81],"that":[72,82,136,172],"minimises":[73],"disparities":[74],"past":[76],"outcomes":[77],"and":[78,100,114,131,151],"prospective":[80,152],"ensures":[83],"future":[86],"decision-making.":[87],"We":[88],"evaluate":[89],"our":[90],"approach":[91],"games:":[94],"the":[95,123,144,149,165,181,192,200],"Allelopathic":[96],"Harvest,":[97],"cooperative":[99],"competitive":[101],"MAS":[102],"focused":[103],"resource":[105],"collection,":[106],"where":[107],"some":[108],"possess":[110],"attribute,":[113],"HospitalSim,":[115],"hospital":[117,126],"simulation,":[118],"coordinate":[122],"operations":[124],"of":[125,159,173,183,202],"patients":[127],"different":[129],"mobility":[130],"priority":[132],"needs.":[133],"Experiments":[134],"show":[135],"Fair-PPO":[137,203],"achieves":[138],"fairer":[139],"policies":[140],"than":[141],"PPO":[142],"across":[143],"metrics":[146],"and,":[147],"through":[148],"components,":[154],"reveals":[155],"wide":[157],"spectrum":[158],"strategies":[160],"to":[161,204],"improve":[162],"fairness;":[163],"at":[164,180],"same":[166],"time,":[167],"its":[168],"performance":[169],"pairs":[170],"state-of-the-art":[174],"fair":[175],"reinforcement-learning":[176],"algorithms.":[177],"comes":[179],"cost":[182],"reduced":[184],"efficiency,":[185],"but":[186],"does":[187],"not":[188],"compromise":[189],"equality":[190],"overall":[193],"population":[194],"(Gini":[195],"index).":[196],"These":[197],"findings":[198],"underscore":[199],"potential":[201],"address":[205],"challenges":[207],"MAS.":[209]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-13T00:00:00"}