{"id":"https://openalex.org/W7138923903","doi":"https://doi.org/10.1609/aaai.v40i43.40987","title":"Offline Multi-Objective Bandits: From Logged Data to Pareto-Optimal Policies","display_name":"Offline Multi-Objective Bandits: From Logged Data to Pareto-Optimal Policies","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138923903","doi":"https://doi.org/10.1609/aaai.v40i43.40987"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i43.40987","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i43.40987","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40987/44948","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40987/44948","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103247963","display_name":"Ji Cheng","orcid":"https://orcid.org/0000-0003-3120-8966"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I4210105229","display_name":"City University of Hong Kong, Shenzhen Research Institute","ror":"https://ror.org/00xc0ma20","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105229"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Ji Cheng","raw_affiliation_strings":["City University of Hong Kong,\nThe City University of Hong Kong Shenzhen Research Institute"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,\nThe City University of Hong Kong Shenzhen Research Institute","institution_ids":["https://openalex.org/I168719708","https://openalex.org/I4210105229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130136690","display_name":"Song Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I4210105229","display_name":"City University of Hong Kong, Shenzhen Research Institute","ror":"https://ror.org/00xc0ma20","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105229"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Song Lai","raw_affiliation_strings":["City University of Hong Kong,\nThe City University of Hong Kong Shenzhen Research Institute"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,\nThe City University of Hong Kong Shenzhen Research Institute","institution_ids":["https://openalex.org/I168719708","https://openalex.org/I4210105229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103082616","display_name":"Shunyu Yao","orcid":"https://orcid.org/0000-0003-0427-2217"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I4210105229","display_name":"City University of Hong Kong, Shenzhen Research Institute","ror":"https://ror.org/00xc0ma20","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105229"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Shunyu Yao","raw_affiliation_strings":["City University of Hong Kong,\nThe City University of Hong Kong Shenzhen Research Institute"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,\nThe City University of Hong Kong Shenzhen Research Institute","institution_ids":["https://openalex.org/I168719708","https://openalex.org/I4210105229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101843145","display_name":"Bo Xue","orcid":"https://orcid.org/0000-0002-7295-4853"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I4210105229","display_name":"City University of Hong Kong, Shenzhen Research Institute","ror":"https://ror.org/00xc0ma20","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105229"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Bo Xue","raw_affiliation_strings":["City University of Hong Kong,\nThe City University of Hong Kong Shenzhen Research Institute"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,\nThe City University of Hong Kong Shenzhen Research Institute","institution_ids":["https://openalex.org/I168719708","https://openalex.org/I4210105229"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103247963"],"corresponding_institution_ids":["https://openalex.org/I168719708","https://openalex.org/I4210105229"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86868687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"43","first_page":"36636","last_page":"36644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.8446000218391418,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.8446000218391418,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.04769999906420708,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.02280000038444996,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6327999830245972},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.6108999848365784},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5821999907493591},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5684000253677368},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.5033000111579895},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4025999903678894},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.38999998569488525},{"id":"https://openalex.org/keywords/pareto-efficiency","display_name":"Pareto efficiency","score":0.3573000133037567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016000151634216},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6327999830245972},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.6108999848365784},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5821999907493591},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5684000253677368},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4478999972343445},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C2778599509","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto efficiency","level":3,"score":0.3573000133037567},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3499000072479248},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3490000069141388},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.310699999332428},{"id":"https://openalex.org/C62360110","wikidata":"https://www.wikidata.org/wiki/Q96777007","display_name":"Circumscription","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i43.40987","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i43.40987","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40987/44948","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i43.40987","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i43.40987","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40987/44948","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7243297100067139}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138923903.pdf","grobid_xml":"https://content.openalex.org/works/W7138923903.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Offline":[0,50],"policy":[1,109,126],"learning":[2,63,122],"from":[3,66,89],"logged":[4],"data":[5,171],"is":[6,73],"a":[7,28,46,55,67,74,107,111,123],"critical":[8],"paradigm":[9],"for":[10,49,110,134,155],"enabling":[11],"effective":[12],"decision-making":[13,35],"without":[14],"costly":[15],"online":[16],"exploration.":[17],"However,":[18],"its":[19],"application":[20],"has":[21],"been":[22],"largely":[23],"confined":[24],"to":[25,31,58,86,105,164],"single-objective":[26],"problems,":[27],"stark":[29],"contrast":[30],"real-world":[32],"scenarios":[33],"where":[34,193],"inherently":[36],"involves":[37],"navigating":[38],"multiple,":[39],"often":[40],"conflicting,":[41],"objectives.":[42],"This":[43],"paper":[44],"introduces":[45],"comprehensive":[47],"framework":[48],"Multi-Objective":[51],"Bandits":[52],"(OffMOB),":[53],"providing":[54],"principled":[56],"solution":[57],"the":[59,80,96,118,144,150,165,187],"fundamental":[60],"challenge":[61],"of":[62,99,129,190],"Pareto-optimal":[64],"policies":[65],"static":[68],"dataset.":[69],"Our":[70],"core":[71],"contribution":[72],"novel":[75],"algorithm":[76,162],"that":[77,160,180],"uniquely":[78],"integrates":[79],"pessimism":[81],"principle":[82],"with":[83],"multi-objective":[84],"optimization":[85],"safely":[87],"learn":[88],"off-policy":[90],"data.":[91],"Crucially,":[92],"our":[93,161],"approach":[94],"transcends":[95],"primary":[97],"limitation":[98],"scalarization":[100],"techniques,":[101],"which":[102],"are":[103],"restricted":[104],"finding":[106],"single":[108],"pre-defined":[112],"preference.":[113],"Instead,":[114],"OffMOB":[115,181],"directly":[116],"approximates":[117],"entire":[119],"Pareto":[120,167],"front,":[121],"single,":[124],"flexible":[125],"model":[127],"capable":[128],"generating":[130],"an":[131],"optimal":[132,191],"action":[133],"any":[135],"desired":[136],"trade-off.":[137],"To":[138],"rigorously":[139],"evaluate":[140],"performance,":[141],"we":[142],"introduce":[143],"Tchebycheff":[145],"sub-optimality":[146],"metric":[147],"and":[148],"establish":[149],"first":[151],"finite-sample":[152],"generalization":[153],"bounds":[154],"this":[156],"problem":[157],"class,":[158],"proving":[159],"converges":[163],"true":[166],"front":[168],"under":[169],"practical":[170],"coverage":[172],"assumptions.":[173],"Extensive":[174],"experiments":[175],"on":[176],"complex":[177],"benchmarks":[178],"demonstrate":[179],"significantly":[182],"outperforms":[183],"existing":[184],"methods,":[185],"identifying":[186],"complete":[188],"set":[189],"trade-offs":[192],"naive":[194],"extensions":[195],"fail.":[196]},"counts_by_year":[],"updated_date":"2026-03-20T20:54:20.808490","created_date":"2026-03-20T00:00:00"}