{"id":"https://openalex.org/W4282813721","doi":"https://doi.org/10.1145/3534678.3539211","title":"ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning","display_name":"ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4282813721","doi":"https://doi.org/10.1145/3534678.3539211"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539211","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539211","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539211","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539211","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/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haozhe Wang","raw_affiliation_strings":["ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"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"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039339683","display_name":"Shuo Yuan","orcid":"https://orcid.org/0000-0002-5668-9527"},"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":"Shuo Yuan","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015970030","display_name":"Xuming He","orcid":"https://orcid.org/0000-0003-2150-1237"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuming He","raw_affiliation_strings":["ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073856221","display_name":"Bo Zheng","orcid":"https://orcid.org/0000-0002-4037-6315"},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4021","last_page":"4031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9991999864578247,"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/T11182","display_name":"Auction Theory and Applications","score":0.9991999864578247,"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/T11161","display_name":"Consumer Market Behavior and Pricing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7660037279129028},{"id":"https://openalex.org/keywords/bidding","display_name":"Bidding","score":0.7142215967178345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6638085842132568},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.5721836090087891},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5558727383613586},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5218290686607361},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4292842745780945},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4270632266998291},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39795851707458496},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32156217098236084},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.20468541979789734},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.17620933055877686},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13568317890167236}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7660037279129028},{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.7142215967178345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6638085842132568},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.5721836090087891},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5558727383613586},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5218290686607361},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4292842745780945},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4270632266998291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39795851707458496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32156217098236084},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.20468541979789734},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.17620933055877686},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13568317890167236},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3534678.3539211","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539211","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539211","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.05240","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.05240","pdf_url":"https://arxiv.org/pdf/2206.05240","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":"doi:10.1145/3534678.3539211","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539211","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539211","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4282813721.pdf","grobid_xml":"https://content.openalex.org/works/W4282813721.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1497039698","https://openalex.org/W1582436621","https://openalex.org/W1723619723","https://openalex.org/W2021375049","https://openalex.org/W2111764152","https://openalex.org/W2149822245","https://openalex.org/W2164294821","https://openalex.org/W2168359464","https://openalex.org/W2198041288","https://openalex.org/W2285664202","https://openalex.org/W2296073425","https://openalex.org/W2512971201","https://openalex.org/W2514140583","https://openalex.org/W2532780566","https://openalex.org/W2562337727","https://openalex.org/W2604272474","https://openalex.org/W2740620324","https://openalex.org/W2751516180","https://openalex.org/W2781726626","https://openalex.org/W2788376840","https://openalex.org/W2800784370","https://openalex.org/W2804791273","https://openalex.org/W2913300629","https://openalex.org/W2945020056","https://openalex.org/W2945611146","https://openalex.org/W2947557559","https://openalex.org/W2951707279","https://openalex.org/W2962854145","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2980555752","https://openalex.org/W2997780057","https://openalex.org/W3009692840","https://openalex.org/W3037897643","https://openalex.org/W3099947523","https://openalex.org/W3101243714","https://openalex.org/W3101380508","https://openalex.org/W3105140685","https://openalex.org/W3110995086","https://openalex.org/W3123298421","https://openalex.org/W3133818088","https://openalex.org/W3162902207","https://openalex.org/W3166393923","https://openalex.org/W3167957332","https://openalex.org/W3185032618","https://openalex.org/W4237922950","https://openalex.org/W4293545785","https://openalex.org/W4298857966","https://openalex.org/W4300107981","https://openalex.org/W4361868498","https://openalex.org/W4385245566","https://openalex.org/W4391602018"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2765830098","https://openalex.org/W2967463586","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W4206221578","https://openalex.org/W3029572990","https://openalex.org/W2615757685"],"abstract_inverted_index":{"Real-Time":[0],"Bidding":[1,101],"(RTB)":[2],"is":[3],"an":[4,117],"important":[5],"mechanism":[6],"in":[7,16,60,99,102,141,161],"modern":[8],"online":[9],"advertising":[10,21],"systems.":[11],"Advertisers":[12],"employ":[13],"bidding":[14,39],"strategies":[15],"RTB":[17],"to":[18,24,69,71,80,83,135],"optimize":[19],"their":[20,81],"effects":[22],"subject":[23],"various":[25],"financial":[26],"requirements,":[27],"especially":[28],"the":[29,37,138],"return-on-investment":[30],"(ROI)":[31],"constraint.":[32],"ROIs":[33],"change":[34],"non-monotonically":[35],"during":[36],"sequential":[38],"process,":[40],"and":[41,50,87,91,126,164,168,173],"often":[42],"induce":[43],"a":[44,107,128,148],"see-saw":[45],"effect":[46],"between":[47],"constraint":[48],"satisfaction":[49],"objective":[51],"optimization.":[52],"While":[53],"some":[54],"existing":[55],"approaches":[56],"show":[57],"promising":[58],"results":[59],"static":[61],"or":[62],"mildly":[63],"changing":[64],"ad":[65,74,143],"markets,":[66],"they":[67],"fail":[68],"generalize":[70],"highly":[72],"dynamic":[73],"markets":[75],"with":[76,152],"ROI":[77],"constraints,":[78],"due":[79],"inability":[82],"adaptively":[84,136],"balance":[85],"constraints":[86],"objectives":[88],"amidst":[89],"non-stationarity":[90],"partial":[92],"observability.":[93],"In":[94],"this":[95],"work,":[96],"we":[97],"specialize":[98],"ROI-Constrained":[100],"non-stationary":[103,142],"markets.":[104,144],"Based":[105],"on":[106,147],"Partially":[108],"Observable":[109],"Constrained":[110],"Markov":[111],"Decision":[112],"Process,":[113],"our":[114],"method":[115],"exploits":[116],"indicator-augmented":[118],"reward":[119],"function":[120],"free":[121],"of":[122],"extra":[123],"trade-off":[124,140],"parameters":[125],"develops":[127],"Curriculum-Guided":[129],"Bayesian":[130],"Reinforcement":[131],"Learning":[132],"(CBRL)":[133],"framework":[134],"control":[137],"constraint-objective":[139],"Extensive":[145],"experiments":[146],"large-scale":[149],"industrial":[150],"dataset":[151],"two":[153],"problem":[154],"settings":[155],"reveal":[156],"that":[157],"CBRL":[158],"generalizes":[159],"well":[160],"both":[162],"in-distribution":[163],"out-of-distribution":[165],"data":[166],"regimes,":[167],"enjoys":[169],"superior":[170],"learning":[171],"efficiency":[172],"stability.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-06-14T00:00:00"}