{"id":"https://openalex.org/W3204743286","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534126","title":"Optimizing Enhanced Cost Per Click via Reinforcement Learning Without Exploration","display_name":"Optimizing Enhanced Cost Per Click via Reinforcement Learning Without Exploration","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3204743286","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534126","mag":"3204743286"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5088975367","display_name":"Sinan Li","orcid":"https://orcid.org/0000-0001-9519-2321"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Sinan Li","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101456902","display_name":"Chun Yuan","orcid":"https://orcid.org/0000-0002-3590-6676"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Chun Yuan","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105923667","display_name":"Xin Zhu","orcid":"https://orcid.org/0000-0002-4376-0806"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhu","raw_affiliation_strings":["Business Growth BU, JD.com, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Business Growth BU, JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6761,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67551882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.998199999332428,"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":0.998199999332428,"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":0.9972000122070312,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bidding","display_name":"Bidding","score":0.8495962619781494},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8084918260574341},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.776975154876709},{"id":"https://openalex.org/keywords/real-time-bidding","display_name":"Real-time bidding","score":0.7666599750518799},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6946911811828613},{"id":"https://openalex.org/keywords/click-through-rate","display_name":"Click-through rate","score":0.6328633427619934},{"id":"https://openalex.org/keywords/premise","display_name":"Premise","score":0.5252901315689087},{"id":"https://openalex.org/keywords/display-advertising","display_name":"Display advertising","score":0.4610874056816101},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3860674798488617},{"id":"https://openalex.org/keywords/online-advertising","display_name":"Online advertising","score":0.3459016978740692},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34231042861938477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32282885909080505},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16018223762512207},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.1512579619884491},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.10070633888244629}],"concepts":[{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.8495962619781494},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8084918260574341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.776975154876709},{"id":"https://openalex.org/C1525070","wikidata":"https://www.wikidata.org/wiki/Q2134714","display_name":"Real-time bidding","level":3,"score":0.7666599750518799},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6946911811828613},{"id":"https://openalex.org/C115174607","wikidata":"https://www.wikidata.org/wiki/Q1100934","display_name":"Click-through rate","level":2,"score":0.6328633427619934},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.5252901315689087},{"id":"https://openalex.org/C2777999536","wikidata":"https://www.wikidata.org/wiki/Q2399498","display_name":"Display advertising","level":4,"score":0.4610874056816101},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3860674798488617},{"id":"https://openalex.org/C512338625","wikidata":"https://www.wikidata.org/wiki/Q624902","display_name":"Online advertising","level":3,"score":0.3459016978740692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34231042861938477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32282885909080505},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16018223762512207},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.1512579619884491},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.10070633888244629},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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":36,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W1757796397","https://openalex.org/W2077055010","https://openalex.org/W2145339207","https://openalex.org/W2149822245","https://openalex.org/W2155968351","https://openalex.org/W2169657221","https://openalex.org/W2317606158","https://openalex.org/W2562337727","https://openalex.org/W2599366803","https://openalex.org/W2604202871","https://openalex.org/W2745512453","https://openalex.org/W2746553466","https://openalex.org/W2788125442","https://openalex.org/W2788376840","https://openalex.org/W2896702309","https://openalex.org/W2904453761","https://openalex.org/W2947150733","https://openalex.org/W2950471160","https://openalex.org/W2953198391","https://openalex.org/W2953981431","https://openalex.org/W2963704132","https://openalex.org/W2963841569","https://openalex.org/W2979211489","https://openalex.org/W3099947523","https://openalex.org/W3101681922","https://openalex.org/W3103752844","https://openalex.org/W3105140685","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6696324988","https://openalex.org/W6742573531","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6764976746","https://openalex.org/W6768617876"],"related_works":["https://openalex.org/W2100597815","https://openalex.org/W2317606158","https://openalex.org/W175164097","https://openalex.org/W2143648166","https://openalex.org/W2952316437","https://openalex.org/W4300589523","https://openalex.org/W2951754014","https://openalex.org/W2078847107","https://openalex.org/W3120879483","https://openalex.org/W2534189265"],"abstract_inverted_index":{"Real-Time":[0],"Bidding":[1],"(RTB)":[2],"is":[3,42,89,103],"an":[4,154,187],"important":[5],"mechanism":[6,51],"in":[7,48,73,83,181],"online":[8,225],"search":[9],"advertising":[10,94],"involved":[11],"with":[12,61,135],"the":[13,21,49,53,66,78,93,99,110,115,120,124,160,178,182,194,200,213,219],"interaction":[14],"among":[15],"platform,":[16],"advertisers,":[17],"and":[18,112,138,198,224],"customers,":[19],"where":[20,52],"proper":[22],"bid":[23,57,81,101],"for":[24,32,59],"each":[25],"page":[26],"views":[27],"plays":[28],"a":[29,86,131,165],"crucial":[30],"role":[31],"good":[33],"marketing":[34],"results.":[35],"Enhanced":[36],"Cost":[37],"Per":[38],"Click":[39],"(ECPC)":[40],"bidding":[41,46,129,195],"one":[43],"of":[44,68,77,96,114,127,202,215,221],"typical":[45],"strategies":[47],"RTB":[50],"advertisers":[54],"will":[55],"raise":[56],"prices":[58],"traffic":[60],"high":[62],"conversion":[63],"rates":[64],"under":[65],"premise":[67],"total":[69],"advertisers'":[70],"cost":[71,95],"control":[72,92],"different":[74,146],"time":[75],"periods":[76],"day.":[79],"The":[80],"ratio":[82,102],"ECPC":[84,128],"as":[85,130],"correction":[87],"coefficient":[88],"used":[90],"to":[91,105,109,142,152,158],"advertisers.":[97],"However,":[98],"optimal":[100],"hard":[104],"be":[106],"derived":[107],"due":[108],"complexity":[111],"volatility":[113],"auction":[116,155],"environment.":[117,183],"To":[118],"address":[119],"challenges,":[121],"we":[122,163],"formulate":[123],"hourly-aggregated":[125],"level":[126],"Markov":[132],"Decision":[133],"Process":[134],"innovative":[136],"state":[137],"reward":[139],"function":[140],"according":[141],"business.":[143],"Besides,":[144],"quite":[145],"from":[147,218],"prior":[148],"work":[149],"that":[150,173],"has":[151],"construct":[153],"model-based":[156],"environment":[157],"solve":[159],"MDP":[161],"problem,":[162],"propose":[164],"novel":[166],"framework":[167,217],"based":[168],"on":[169,177,209],"model-free":[170],"reinforcement":[171],"learning":[172],"does":[174],"not":[175],"rely":[176],"agent's":[179],"explorations":[180],"We":[184],"furthermore":[185],"design":[186],"adaptive":[188],"action":[189],"choosing":[190],"strategy":[191],"which":[192],"adjusts":[193],"behavior":[196],"dynamically":[197],"improves":[199],"performance":[201],"categories/groups's":[203],"consumption":[204],"qualified":[205],"rate.":[206],"Experimental":[207],"results":[208],"real":[210],"dataset":[211],"demonstrate":[212],"effectiveness":[214],"our":[216],"perspective":[220],"consistency,":[222],"stability":[223],"effect.":[226]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}