{"id":"https://openalex.org/W4306317257","doi":"https://doi.org/10.1145/3511808.3557064","title":"An Actor-critic Reinforcement Learning Model for Optimal Bidding in Online Display Advertising","display_name":"An Actor-critic Reinforcement Learning Model for Optimal Bidding in Online Display Advertising","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317257","doi":"https://doi.org/10.1145/3511808.3557064"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557064","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557064","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046146364","display_name":"Congde Yuan","orcid":"https://orcid.org/0000-0001-5298-3342"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congde Yuan","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051055133","display_name":"Mengzhuo Guo","orcid":"https://orcid.org/0000-0003-3559-733X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengzhuo Guo","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107877081","display_name":"Chaoneng Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoneng Xiang","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052324447","display_name":"Shuangyang Wang","orcid":"https://orcid.org/0000-0002-6180-8607"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuangyang Wang","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109543121","display_name":"Guoqing Song","orcid":"https://orcid.org/0000-0002-8823-3540"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqing Song","raw_affiliation_strings":["Tencent, China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, China, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052391290","display_name":"Qingpeng Zhang","orcid":"https://orcid.org/0000-0002-6819-0686"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingpeng Zhang","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3604","last_page":"3613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11161","display_name":"Consumer Market Behavior and Pricing","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9977999925613403,"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":0.9940999746322632,"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":0.9058377742767334},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8075258731842041},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8045396208763123},{"id":"https://openalex.org/keywords/real-time-bidding","display_name":"Real-time bidding","score":0.7117727994918823},{"id":"https://openalex.org/keywords/display-advertising","display_name":"Display advertising","score":0.6438350677490234},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5652502179145813},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5001699924468994},{"id":"https://openalex.org/keywords/impression","display_name":"Impression","score":0.4878852367401123},{"id":"https://openalex.org/keywords/online-advertising","display_name":"Online advertising","score":0.35609889030456543},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.35518670082092285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3446325361728668},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.335918664932251},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.17305782437324524},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.16738155484199524},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.12216141819953918},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09830138087272644}],"concepts":[{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.9058377742767334},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8075258731842041},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8045396208763123},{"id":"https://openalex.org/C1525070","wikidata":"https://www.wikidata.org/wiki/Q2134714","display_name":"Real-time bidding","level":3,"score":0.7117727994918823},{"id":"https://openalex.org/C2777999536","wikidata":"https://www.wikidata.org/wiki/Q2399498","display_name":"Display advertising","level":4,"score":0.6438350677490234},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5652502179145813},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5001699924468994},{"id":"https://openalex.org/C2776684213","wikidata":"https://www.wikidata.org/wiki/Q6007582","display_name":"Impression","level":2,"score":0.4878852367401123},{"id":"https://openalex.org/C512338625","wikidata":"https://www.wikidata.org/wiki/Q624902","display_name":"Online advertising","level":3,"score":0.35609889030456543},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.35518670082092285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3446325361728668},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.335918664932251},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17305782437324524},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.16738155484199524},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.12216141819953918},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09830138087272644},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3511808.3557064","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557064","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W114465074","https://openalex.org/W1572878464","https://openalex.org/W2021375049","https://openalex.org/W2119914577","https://openalex.org/W2136189984","https://openalex.org/W2139891288","https://openalex.org/W2145339207","https://openalex.org/W2149822245","https://openalex.org/W2158268067","https://openalex.org/W2158635658","https://openalex.org/W2317606158","https://openalex.org/W2562337727","https://openalex.org/W2588101506","https://openalex.org/W2604202871","https://openalex.org/W2723293840","https://openalex.org/W2746553466","https://openalex.org/W2770888277","https://openalex.org/W2788376840","https://openalex.org/W2892075429","https://openalex.org/W2945611146","https://openalex.org/W2952551358","https://openalex.org/W2962989965","https://openalex.org/W2963841569","https://openalex.org/W2987195113","https://openalex.org/W3032916997","https://openalex.org/W3098378121","https://openalex.org/W3099947523","https://openalex.org/W3101243714","https://openalex.org/W3101681922","https://openalex.org/W3166393923"],"related_works":["https://openalex.org/W2990183840","https://openalex.org/W3099947523","https://openalex.org/W2149822245","https://openalex.org/W3005478775","https://openalex.org/W2740620324","https://openalex.org/W4206910518","https://openalex.org/W4375959521","https://openalex.org/W3099082736","https://openalex.org/W2989878839","https://openalex.org/W4226021416"],"abstract_inverted_index":{"The":[0,230],"real-time":[1],"bidding":[2,97,179,272],"(RTB)":[3],"paradigm":[4],"allows":[5],"the":[6,23,28,42,52,56,69,77,96,115,133,146,155,158,163,172,191,199,206,218,235,238,253,282],"advertisers":[7,24],"to":[8,26,55,73,88,132,140,170,197,203,216],"submit":[9],"a":[10,100,119,137,167,176],"bid":[11],"for":[12,113,270],"each":[13],"impression":[14,91,142],"in":[15,46,175,241,252,274,285],"online":[16,202,226,231,255],"display":[17,256],"advertising.":[18],"A":[19],"usual":[20],"demand":[21],"of":[22,31,71,82,157,220,237,243,262],"is":[25,81],"maximize":[27],"total":[29],"value":[30],"winning":[32],"impressions":[33],"under":[34,118],"constraints":[35],"on":[36],"some":[37],"key":[38],"performance":[39],"indicators.":[40,247],"Unfortunately,":[41],"existing":[43],"RTB":[44,72,275],"research":[45],"industrial":[47],"applications":[48],"can":[49,280],"hardly":[50],"achieve":[51],"optimum":[53],"due":[54],"stochastic":[57],"decision":[58,121,174],"scenarios":[59],"and":[60,104,152,154,190,222,259,279],"complex":[61],"consumer":[62],"behaviors.":[63],"In":[64],"this":[65,286],"study,":[66],"we":[67,135,211],"address":[68],"application":[70],"mobile":[74],"gaming":[75],"where":[76],"in-app":[78,147],"purchase":[79],"action":[80],"high":[83],"uncertainty,":[84],"making":[85],"it":[86],"challenging":[87],"evaluate":[89],"individual":[90],"opportunities.":[92],"We":[93,193,266],"first":[94],"formulate":[95],"process":[98],"into":[99],"constrained":[101],"optimization":[102],"problem":[103],"then":[105],"propose":[106],"an":[107,225],"actor-critic":[108],"reinforcement":[109],"learning":[110],"(ACRL)":[111],"model":[112,201],"obtaining":[114],"optimal":[116,271],"policy":[117],"dynamic":[120],"environment.":[122],"To":[123],"avoid":[124],"feeding":[125],"too":[126],"many":[127],"samples":[128],"with":[129],"zero":[130],"labels":[131],"model,":[134],"provide":[136],"new":[138],"way":[139],"quantify":[141],"opportunities":[143],"by":[144,181],"integrating":[145],"actions,":[148],"such":[149],"as":[150],"conversion":[151],"purchase,":[153],"characteristics":[156],"candidate":[159],"ad":[160],"inventories.":[161],"Moreover,":[162],"proposed":[164,239,268],"ACRL":[165,221,240,248],"learns":[166],"Gaussian":[168],"distribution":[169],"simulate":[171],"audience's":[173],"more":[177],"real":[178],"scenario":[180],"taking":[182],"additional":[183],"contextual":[184],"side":[185],"information":[186],"about":[187],"both":[188],"media":[189],"audience.":[192],"also":[194],"introduce":[195],"how":[196],"deploy":[198],"learned":[200],"help":[204],"adjust":[205],"final":[207],"bid.":[208],"At":[209],"last,":[210],"conduct":[212],"comprehensive":[213],"offline":[214],"experiments":[215],"demonstrate":[217],"effectiveness":[219],"carefully":[223],"set":[224],"A/B":[227],"testing":[228],"experiment.":[229],"experimental":[232],"results":[233],"verify":[234],"efficacy":[236],"terms":[242],"multiple":[244],"critical":[245],"commercial":[246],"has":[249],"been":[250],"deployed":[251],"Tencent":[254],"advertising":[257],"platform":[258],"impacts":[260],"billions":[261],"traffic":[263],"every":[264],"day.":[265],"believe":[267],"modifications":[269],"problems":[273],"are":[276],"practically":[277],"innovative":[278],"inspire":[281],"relative":[283],"works":[284],"field.":[287]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}