{"id":"https://openalex.org/W4380558850","doi":"https://doi.org/10.1145/3580305.3599254","title":"Adversarial Constrained Bidding via Minimax Regret Optimization with Causality-Aware Reinforcement Learning","display_name":"Adversarial Constrained Bidding via Minimax Regret Optimization with Causality-Aware Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4380558850","doi":"https://doi.org/10.1145/3580305.3599254"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599254","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.07106","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101719393","display_name":"Haozhe Wang","orcid":"https://orcid.org/0000-0002-9299-6305"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haozhe Wang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101628460","display_name":"Chao Du","orcid":"https://orcid.org/0000-0003-1244-6336"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Du","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057927034","display_name":"Panyan Fang","orcid":"https://orcid.org/0009-0001-6552-787X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Panyan Fang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100317919","display_name":"Li He","orcid":"https://orcid.org/0000-0003-4729-0415"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"LI He","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114334482","display_name":"Liang Wang","orcid":"https://orcid.org/0009-0000-5112-7763"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103171503","display_name":"Bo Zheng","orcid":"https://orcid.org/0009-0007-5430-3890"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zheng","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101719393"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":1.5127,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83419571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2314","last_page":"2325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9997000098228455,"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":0.9997000098228455,"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/T11182","display_name":"Auction Theory and Applications","score":0.9990000128746033,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/bidding","display_name":"Bidding","score":0.8703688383102417},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7705418467521667},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7415753602981567},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.7229605913162231},{"id":"https://openalex.org/keywords/common-value-auction","display_name":"Common value auction","score":0.699636697769165},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6337066888809204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46836817264556885},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45148640871047974},{"id":"https://openalex.org/keywords/real-time-bidding","display_name":"Real-time bidding","score":0.4346124529838562},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.4227994978427887},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3423153758049011},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.17746147513389587},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.15705537796020508},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09007900953292847}],"concepts":[{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.8703688383102417},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7705418467521667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415753602981567},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7229605913162231},{"id":"https://openalex.org/C163239763","wikidata":"https://www.wikidata.org/wiki/Q5153637","display_name":"Common value auction","level":2,"score":0.699636697769165},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6337066888809204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46836817264556885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45148640871047974},{"id":"https://openalex.org/C1525070","wikidata":"https://www.wikidata.org/wiki/Q2134714","display_name":"Real-time bidding","level":3,"score":0.4346124529838562},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.4227994978427887},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3423153758049011},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.17746147513389587},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.15705537796020508},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09007900953292847}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3580305.3599254","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2306.07106","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.07106","pdf_url":"https://arxiv.org/pdf/2306.07106","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.07106","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.07106","pdf_url":"https://arxiv.org/pdf/2306.07106","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4380558850.pdf","grobid_xml":"https://content.openalex.org/works/W4380558850.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1983989471","https://openalex.org/W2005311763","https://openalex.org/W2014873662","https://openalex.org/W2021663595","https://openalex.org/W2030876146","https://openalex.org/W2562337727","https://openalex.org/W2926117393","https://openalex.org/W2945611146","https://openalex.org/W2963393294","https://openalex.org/W2966080558","https://openalex.org/W2997780057","https://openalex.org/W3093887912","https://openalex.org/W3096831136","https://openalex.org/W3101243714","https://openalex.org/W3110995086","https://openalex.org/W3133818088","https://openalex.org/W3143334439","https://openalex.org/W3166393923","https://openalex.org/W3167957332","https://openalex.org/W4282813721","https://openalex.org/W4385568167","https://openalex.org/W6784678651"],"related_works":["https://openalex.org/W1995388959","https://openalex.org/W2147694495","https://openalex.org/W1984203460","https://openalex.org/W1562320220","https://openalex.org/W2372662578","https://openalex.org/W784208287","https://openalex.org/W341704063","https://openalex.org/W2141395620","https://openalex.org/W2355176056","https://openalex.org/W4310829256"],"abstract_inverted_index":{"The":[0],"proliferation":[1],"of":[2,10,17,29,74,92,108,122,166],"the":[3,8,15,40,71,90,104,111,119,125,163,193],"Internet":[4],"has":[5],"led":[6],"to":[7,32,47,52,117,172],"emergence":[9],"online":[11,18,75],"advertising,":[12],"driven":[13],"by":[14,189,217],"mechanics":[16],"auctions.":[19],"In":[20,85,168],"these":[21],"repeated":[22],"auctions,":[23],"software":[24],"agents":[25],"participate":[26],"on":[27,58,63,110,134,197],"behalf":[28],"aggregated":[30],"advertisers":[31],"optimize":[33,48],"for":[34,154,176],"their":[35],"long-term":[36],"utility.":[37],"To":[38],"fulfill":[39],"diverse":[41],"demands,":[42],"bidding":[43,60,94,97,178],"strategies":[44],"are":[45],"employed":[46],"advertising":[49],"objectives":[50],"subject":[51],"different":[53,79],"spending":[54],"constraints.":[55],"Existing":[56],"approaches":[57],"constrained":[59,93],"typically":[61],"rely":[62],"i.i.d.":[64,112],"train":[65,120],"and":[66,156,201],"test":[67,127],"conditions,":[68],"which":[69,99],"contradicts":[70],"adversarial":[72,96,105,152],"nature":[73],"ad":[76],"markets":[77],"where":[78],"parties":[80],"possess":[81],"potentially":[82],"conflicting":[83],"objectives.":[84],"this":[86,135],"regard,":[87],"we":[88,137,170,185],"explore":[89],"problem":[91],"in":[95],"environments,":[98],"assumes":[100],"no":[101],"knowledge":[102,191],"about":[103],"factors.":[106],"Instead":[107],"relying":[109],"assumption,":[113],"our":[114,206],"insight":[115],"is":[116],"align":[118],"distribution":[121,128,165],"environments":[123,153],"with":[124,209],"potential":[126],"meanwhile":[129],"minimizing":[130],"policy":[131,161,183],"regret.":[132],"Based":[133],"insight,":[136],"propose":[138],"a":[139,149,157,181],"practical":[140],"Minimax":[141],"Regret":[142],"Optimization":[143],"(MiRO)":[144],"approach":[145],"that":[146,205],"interleaves":[147],"between":[148],"teacher":[150],"finding":[151],"tutoring":[155],"learner":[158],"meta-learning":[159],"its":[160],"over":[162,218],"given":[164],"environments.":[167],"addition,":[169],"pioneer":[171],"incorporate":[173],"expert":[174],"demonstrations":[175],"learning":[177],"strategies.":[179],"Through":[180],"causality-aware":[182],"design,":[184],"improve":[186],"upon":[187],"MiRO":[188,208],"distilling":[190],"from":[192],"experts.":[194],"Extensive":[195],"experiments":[196],"both":[198],"industrial":[199],"data":[200,203],"synthetic":[202],"show":[204],"method,":[207],"Causality-aware":[210],"reinforcement":[211],"Learning":[212],"(MiROCL),":[213],"outperforms":[214],"prior":[215],"methods":[216],"30%.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}