{"id":"https://openalex.org/W2987195113","doi":"https://doi.org/10.1145/3357384.3358027","title":"Reinforcement Learning with Sequential Information Clustering in Real-Time Bidding","display_name":"Reinforcement Learning with Sequential Information Clustering in Real-Time Bidding","publication_year":2019,"publication_date":"2019-11-03","ids":{"openalex":"https://openalex.org/W2987195113","doi":"https://doi.org/10.1145/3357384.3358027","mag":"2987195113"},"language":"en","primary_location":{"id":"doi:10.1145/3357384.3358027","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3358027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","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/A5005522616","display_name":"Junwei Lu","orcid":"https://orcid.org/0000-0003-3743-6855"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junwei Lu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053431894","display_name":"Chaoqi Yang","orcid":"https://orcid.org/0000-0002-5017-6114"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoqi Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019439900","display_name":"Xiaofeng Gao","orcid":"https://orcid.org/0000-0003-1776-8799"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Gao","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063230535","display_name":"Liubin Wang","orcid":"https://orcid.org/0000-0001-8904-8569"},"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":"Liubin Wang","raw_affiliation_strings":["Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101881961","display_name":"Changcheng Li","orcid":"https://orcid.org/0000-0001-8861-6771"},"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":"Changcheng Li","raw_affiliation_strings":["Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100428808","display_name":"Guihai Chen","orcid":"https://orcid.org/0000-0002-6934-1685"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guihai Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005522616"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.1703,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89612347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1633","last_page":"1641"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11161","display_name":"Consumer Market Behavior and Pricing","score":0.993399977684021,"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":0.993399977684021,"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":0.9851999878883362,"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":0.98089998960495,"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/bidding","display_name":"Bidding","score":0.9358415007591248},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8592075109481812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.796334981918335},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6277239322662354},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5453183650970459},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5266085863113403},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5226761698722839},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42317935824394226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39930304884910583},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39139097929000854},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09075230360031128}],"concepts":[{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.9358415007591248},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8592075109481812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796334981918335},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6277239322662354},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5453183650970459},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5266085863113403},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5226761698722839},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42317935824394226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39930304884910583},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39139097929000854},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09075230360031128},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3357384.3358027","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3358027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.44999998807907104,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1969591148","https://openalex.org/W1972085072","https://openalex.org/W2011384577","https://openalex.org/W2021375049","https://openalex.org/W2039842578","https://openalex.org/W2117340018","https://openalex.org/W2125510930","https://openalex.org/W2136503687","https://openalex.org/W2149822245","https://openalex.org/W2160808139","https://openalex.org/W2290203315","https://openalex.org/W2509235963","https://openalex.org/W2523437372","https://openalex.org/W2562337727","https://openalex.org/W2576265825","https://openalex.org/W2624731731","https://openalex.org/W2788125442","https://openalex.org/W2802349643","https://openalex.org/W2963841569","https://openalex.org/W3103752844","https://openalex.org/W3105140685","https://openalex.org/W3105851319","https://openalex.org/W3106419620"],"related_works":["https://openalex.org/W2355561715","https://openalex.org/W2355326491","https://openalex.org/W2389286292","https://openalex.org/W2360751371","https://openalex.org/W2387920521","https://openalex.org/W2389754756","https://openalex.org/W2382224273","https://openalex.org/W2373538886","https://openalex.org/W2360290312","https://openalex.org/W2369836678"],"abstract_inverted_index":{"Display":[0],"advertising":[1],"is":[2,8,21,83],"a":[3,80,120,129,135,151],"billion":[4],"dollar":[5],"business":[6],"which":[7],"the":[9,24,29,53,69,74,77,87,96,113,147,159,163,166],"primary":[10],"income":[11],"of":[12,23,31,76,79,101,165,171],"many":[13,58],"companies.":[14],"In":[15],"this":[16],"scenario,":[17,116],"real-time":[18,114],"bidding":[19,56,70,115],"optimization":[20],"one":[22],"most":[25],"important":[26],"problems,":[27],"where":[28],"bids":[30],"ads":[32],"for":[33],"each":[34],"impression":[35],"are":[36,49,105],"determined":[37],"by":[38],"an":[39],"intelligent":[40],"policy":[41],"such":[42],"that":[43,158],"some":[44],"global":[45],"key":[46],"performance":[47,100,173],"indicators":[48],"optimized.":[50],"Due":[51],"to":[52,62,67,145],"highly":[54],"dynamic":[55],"environment,":[57],"recent":[59],"works":[60],"try":[61],"use":[63],"reinforcement":[64,103],"learning":[65],"algorithms":[66,104],"train":[68],"agents.":[71],"However,":[72],"as":[73],"probability":[75],"occurrence":[78],"particular":[81],"state":[82,88,138,164],"typically":[84],"low":[85],"and":[86,99,134],"representation":[89],"in":[90,112,169],"current":[91],"work":[92],"lacks":[93],"sequential":[94,130],"information,":[95],"convergence":[97,175],"speed":[98],"deep":[102],"disappointing.":[106],"To":[107],"tackle":[108],"these":[109],"two":[110],"challenges":[111],"we":[117],"propose":[118],"ClusterA3C,":[119],"novel":[121],"Advantage":[122],"Asynchronous":[123],"Actor-Critic":[124],"(A3C)":[125],"variant":[126],"integrated":[127],"with":[128],"information":[131],"extraction":[132],"scheme":[133,149,161],"clustering":[136],"based":[137],"aggregation":[139],"scheme.":[140],"We":[141],"conduct":[142],"extensive":[143],"experiments":[144],"validate":[146],"proposed":[148,160],"on":[150],"real-world":[152],"commercial":[153],"dataset.":[154],"Experimental":[155],"results":[156],"show":[157],"outperforms":[162],"art":[167],"methods":[168],"terms":[170],"either":[172],"or":[174],"speed.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}