{"id":"https://openalex.org/W4321479987","doi":"https://doi.org/10.1145/3539597.3570486","title":"Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning","display_name":"Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning","publication_year":2023,"publication_date":"2023-02-22","ids":{"openalex":"https://openalex.org/W4321479987","doi":"https://doi.org/10.1145/3539597.3570486"},"language":"en","primary_location":{"id":"doi:10.1145/3539597.3570486","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3570486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029097679","display_name":"Tianchi Cai","orcid":"https://orcid.org/0000-0003-1503-6519"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tianchi Cai","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1503-6519","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072368959","display_name":"Jiyan Jiang","orcid":"https://orcid.org/0000-0002-1083-2834"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiyan Jiang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1083-2834","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078799714","display_name":"Wenpeng Zhang","orcid":"https://orcid.org/0000-0002-3796-161X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenpeng Zhang","raw_affiliation_strings":["Ant Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3796-161X","affiliations":[{"raw_affiliation_string":"Ant Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086273618","display_name":"Shiji Zhou","orcid":"https://orcid.org/0000-0002-0666-0769"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiji Zhou","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0666-0769","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081007833","display_name":"Xierui Song","orcid":"https://orcid.org/0000-0002-4580-1683"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xierui Song","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4580-1683","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081211529","display_name":"Li Yu","orcid":"https://orcid.org/0000-0002-3045-2775"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Yu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3045-2775","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058735109","display_name":"Lihong Gu","orcid":"https://orcid.org/0000-0002-0706-3448"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lihong Gu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0706-3448","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059787539","display_name":"Xiaodong Zeng","orcid":"https://orcid.org/0000-0001-7638-5443"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaodong Zeng","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7638-5443","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053242349","display_name":"Jinjie Gu","orcid":"https://orcid.org/0000-0001-7596-4945"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinjie Gu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7596-4945","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031338085","display_name":"Guannan Zhang","orcid":"https://orcid.org/0000-0002-7091-2318"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guannan Zhang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7091-2318","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5029097679"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1864,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.88213422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"186","last_page":"194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11161","display_name":"Consumer Market Behavior and Pricing","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T11161","display_name":"Consumer Market Behavior and Pricing","score":0.9988999962806702,"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/T11182","display_name":"Auction Theory and Applications","score":0.9952999949455261,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9937000274658203,"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":0.85203617811203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7313047051429749},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.48644113540649414},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.45447972416877747},{"id":"https://openalex.org/keywords/budget-constraint","display_name":"Budget constraint","score":0.447950541973114},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34568554162979126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2725619971752167},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1927265226840973},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.12452748417854309},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.09718918800354004},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07968643307685852}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.85203617811203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7313047051429749},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.48644113540649414},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.45447972416877747},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.447950541973114},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34568554162979126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2725619971752167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1927265226840973},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.12452748417854309},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09718918800354004},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07968643307685852},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539597.3570486","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3570486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1965002555","https://openalex.org/W1999874108","https://openalex.org/W2014313807","https://openalex.org/W2029523065","https://openalex.org/W2048136477","https://openalex.org/W2106887613","https://openalex.org/W2560674852","https://openalex.org/W2723293840","https://openalex.org/W2788376840","https://openalex.org/W2914238450","https://openalex.org/W2963052087","https://openalex.org/W2963654596","https://openalex.org/W2987962448","https://openalex.org/W2988150581","https://openalex.org/W2996959725","https://openalex.org/W2997914278","https://openalex.org/W2998111914","https://openalex.org/W3099947523","https://openalex.org/W3162902207","https://openalex.org/W3173335915","https://openalex.org/W3210703899","https://openalex.org/W4206497039","https://openalex.org/W4212774754","https://openalex.org/W4214717370","https://openalex.org/W4292022450","https://openalex.org/W6600002382"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W4225619808"],"abstract_inverted_index":{"We":[0,16,82],"study":[1],"the":[2,19,29,34,53,93,127,133,150],"budget":[3,25,108,125],"allocation":[4,26],"problem":[5],"in":[6,28,60],"online":[7],"marketing":[8,24,107,115,154],"campaigns":[9],"that":[10,85,132],"utilize":[11],"previously":[12],"collected":[13],"offline":[14,30,41],"data.":[15],"first":[17],"discuss":[18],"long-term":[20],"effect":[21],"of":[22,152],"optimizing":[23],"decisions":[27],"setting.":[31],"To":[32],"overcome":[33],"challenge,":[35],"we":[36],"propose":[37],"a":[38,113],"novel":[39],"game-theoretic":[40],"value-based":[42,102],"reinforcement":[43,103],"learning":[44,104],"method":[45,51,87,135,142],"using":[46],"mixed":[47],"policies.":[48],"The":[49,140],"proposed":[50,134,141],"reduces":[52],"need":[54],"to":[55,63,90,92,147],"store":[56],"infinitely":[57],"many":[58,66],"policies":[59],"previous":[61,101],"methods":[62,105],"only":[64],"constantly":[65],"policies,":[67],"which":[68,96],"achieves":[69],"nearly":[70],"optimal":[71,94],"policy":[72],"efficiency,":[73],"making":[74],"it":[75],"practical":[76],"and":[77,120,130],"favorable":[78],"for":[79,106],"industrial":[80],"usage.":[81],"further":[83],"show":[84,131],"this":[86,153],"is":[88],"guaranteed":[89],"converge":[91],"policy,":[95],"cannot":[97],"be":[98],"achieved":[99],"by":[100],"allocation.":[109],"Our":[110],"experiments":[111],"on":[112],"large-scale":[114],"campaign":[116],"with":[117],"tens-of-millions":[118],"users":[119],"more":[121],"than":[122],"one":[123],"billion":[124],"verify":[126],"theoretical":[128],"results":[129],"outperforms":[136],"various":[137],"baseline":[138],"methods.":[139],"has":[143],"been":[144],"successfully":[145],"deployed":[146],"serve":[148],"all":[149],"traffic":[151],"campaign.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}