{"id":"https://openalex.org/W4403582597","doi":"https://doi.org/10.1145/3627673.3679964","title":"MODRL-TA: A Multi-Objective Deep Reinforcement Learning Framework for Traffic Allocation in E-Commerce Search","display_name":"MODRL-TA: A Multi-Objective Deep Reinforcement Learning Framework for Traffic Allocation in E-Commerce Search","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403582597","doi":"https://doi.org/10.1145/3627673.3679964"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5054004904","display_name":"Peng Cheng","orcid":null},"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":true,"raw_author_name":"Peng Cheng","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075244395","display_name":"Huimu Wang","orcid":"https://orcid.org/0000-0001-7115-8831"},"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":"Huimu Wang","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112860071","display_name":"Jinyuan Zhao","orcid":"https://orcid.org/0000-0003-0259-233X"},"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":"Jinyuan Zhao","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673425","display_name":"Yihao Wang","orcid":"https://orcid.org/0000-0003-1823-8335"},"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":"Yihao Wang","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017552772","display_name":"Enqiang Xu","orcid":"https://orcid.org/0009-0002-4647-3439"},"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":"Enqiang Xu","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101388390","display_name":"Yu Zhao","orcid":"https://orcid.org/0000-0003-3867-1128"},"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":"Yu Zhao","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072367863","display_name":"Zhuojian Xiao","orcid":"https://orcid.org/0000-0003-3013-4264"},"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":"Zhuojian Xiao","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714543","display_name":"Songlin Wang","orcid":"https://orcid.org/0000-0003-0102-9123"},"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":"Songlin Wang","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045596194","display_name":"Guoyu Tang","orcid":"https://orcid.org/0009-0003-9586-4652"},"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":"Guoyu Tang","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037906509","display_name":"Lin Liu","orcid":"https://orcid.org/0000-0003-4173-7650"},"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":"Lin Liu","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010637653","display_name":"Sulong Xu","orcid":"https://orcid.org/0009-0001-1610-6008"},"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":"Sulong Xu","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5054004904"],"corresponding_institution_ids":["https://openalex.org/I4210103986"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20514723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3694","last_page":"3698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.9890999794006348,"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"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9869999885559082,"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":0.8961337804794312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7524666786193848},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41373923420906067},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32347381114959717}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8961337804794312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7524666786193848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41373923420906067},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32347381114959717}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and 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":10,"referenced_works":["https://openalex.org/W1972169135","https://openalex.org/W2044905589","https://openalex.org/W2132083787","https://openalex.org/W2562337727","https://openalex.org/W2760506156","https://openalex.org/W2790759781","https://openalex.org/W3157410348","https://openalex.org/W3173331009","https://openalex.org/W3211700439","https://openalex.org/W4396822210"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Traffic":[0],"allocation":[1],"is":[2],"a":[3,83,94,105],"process":[4],"of":[5,33,52,57,68,90,135,145,220],"redistributing":[6],"natural":[7],"traffic":[8,53],"to":[9,46,119,140,156,162,200],"products":[10],"by":[11],"adjusting":[12],"their":[13],"positions":[14],"in":[15,169,172],"the":[16,31,49,66,77,101,133,142,197,205,217],"post-search":[17],"phase,":[18],"aimed":[19],"at":[20],"effectively":[21],"fostering":[22],"merchant":[23],"growth,":[24],"precisely":[25],"meeting":[26],"customer":[27],"demands,":[28],"and":[29,65,104,204,222],"ensuring":[30],"maximization":[32],"interests":[34],"across":[35],"various":[36],"parties":[37],"within":[38,71],"e-commerce":[39,173,214,230],"platforms.":[40],"Existing":[41],"methods":[42],"based":[43,99],"on":[44,100,211,228],"learning":[45,59,87],"rank":[47],"neglect":[48],"long-term":[50,143,164],"value":[51,144],"allocation,":[54],"whereas":[55],"approaches":[56],"reinforcement":[58,86],"suffer":[60],"from":[61,148,182],"balancing":[62],"multiple":[63,146],"objectives":[64,147,161],"difficulties":[67],"cold":[69,206],"starts":[70],"real-world":[72,212],"data":[73,107,181],"environments.":[74],"To":[75],"address":[76],"aforementioned":[78],"issues,":[79],"this":[80],"paper":[81],"propose":[82],"multi-objective":[84,91],"deep":[85],"framework":[88],"consisting":[89],"Q-learning":[92],"(MOQ),":[93],"decision":[95],"fusion":[96],"algorithm":[97],"(DFM)":[98],"cross-entropy":[102],"method(CEM),":[103],"progressive":[106],"augmentation":[108],"system":[109],"(PDA).":[110],"Specifically.":[111],"MOQ":[112,178],"constructs":[113],"ensemble":[114],"RL":[115],"models,":[116],"each":[117],"dedicated":[118],"an":[120,149,229],"objective,":[121],"such":[122],"as":[123,137],"click-through":[124],"rate,":[125,127],"conversion":[126],"etc.":[128],"These":[129],"models":[130],"individually":[131],"determine":[132],"position":[134],"items":[136],"actions,":[138],"aiming":[139],"estimate":[141],"individual":[150],"perspective.":[151],"Then":[152],"we":[153,223],"employ":[154],"DFM":[155],"dynamically":[157],"adjust":[158],"weights":[159],"among":[160],"maximize":[163],"value,":[165],"addressing":[166],"temporal":[167],"dynamics":[168],"objective":[170],"preferences":[171],"scenarios.":[174],"Initially,":[175],"PDA":[176],"trained":[177],"with":[179],"simulated":[180,198],"offline":[183],"logs.":[184],"As":[185],"experiments":[186],"progressed,":[187],"it":[188],"strategically":[189],"integrated":[190],"real":[191],"user":[192],"interaction":[193],"data,":[194],"ultimately":[195],"replacing":[196],"dataset":[199],"alleviate":[201],"distributional":[202],"shifts":[203],"start":[207],"problem.":[208],"Experimental":[209],"results":[210],"online":[213],"systems":[215],"demonstrate":[216],"significant":[218],"improvements":[219],"MODRL-TA,":[221],"have":[224],"successfully":[225],"deployed":[226],"MODRL-TA":[227],"search":[231],"platform.":[232]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}