{"id":"https://openalex.org/W4412876956","doi":"https://doi.org/10.1145/3711896.3737250","title":"Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems","display_name":"Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412876956","doi":"https://doi.org/10.1145/3711896.3737250"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737250","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737250","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737250","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737250","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075851850","display_name":"Langming Liu","orcid":"https://orcid.org/0000-0003-1995-3381"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Langming Liu","raw_affiliation_strings":["Taobao &amp; Tmall Group of Alibaba, Hangzhou, China and City University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Taobao &amp; Tmall Group of Alibaba, Hangzhou, China and City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059573675","display_name":"Wanyu Wang","orcid":"https://orcid.org/0000-0001-5976-0707"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Wanyu Wang","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China and City University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China and City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I3045169105","https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068318957","display_name":"Chi Zhang","orcid":"https://orcid.org/0000-0002-3524-6874"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Zhang","raw_affiliation_strings":["Harbin Engineering University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108153109","display_name":"Bo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088492734","display_name":"Hongzhi Yin","orcid":"https://orcid.org/0000-0003-1395-261X"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hongzhi Yin","raw_affiliation_strings":["University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003379167","display_name":"Xuetao Wei","orcid":"https://orcid.org/0000-0002-4450-2251"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuetao Wei","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113392255","display_name":"Wenbo Su","orcid":"https://orcid.org/0009-0009-3800-7543"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Su","raw_affiliation_strings":["Taobao &amp; Tmall Group of Alibaba, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Taobao &amp; Tmall Group of Alibaba, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073856221","display_name":"Bo Zheng","orcid":"https://orcid.org/0000-0002-4037-6315"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zheng","raw_affiliation_strings":["Taobao &amp; Tmall Group of Alibaba, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Taobao &amp; Tmall Group of Alibaba, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100645854","display_name":"Xiangyu Zhao","orcid":"https://orcid.org/0000-0003-2926-4416"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhao","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5075851850"],"corresponding_institution_ids":["https://openalex.org/I168719708","https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":6.5016,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9649867,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4635","last_page":"4646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9983999729156494,"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":0.9886000156402588,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.8415655493736267},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8175963759422302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7965517640113831},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6503434181213379},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.5032650828361511},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4376613199710846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.433743953704834},{"id":"https://openalex.org/keywords/online-advertising","display_name":"Online advertising","score":0.4260832369327545},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33713406324386597},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.21249333024024963},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07565796375274658}],"concepts":[{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8415655493736267},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8175963759422302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7965517640113831},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6503434181213379},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.5032650828361511},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4376613199710846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.433743953704834},{"id":"https://openalex.org/C512338625","wikidata":"https://www.wikidata.org/wiki/Q624902","display_name":"Online advertising","level":3,"score":0.4260832369327545},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33713406324386597},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.21249333024024963},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07565796375274658},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3711896.3737250","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737250","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737250","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.23090","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23090","pdf_url":"https://arxiv.org/pdf/2506.23090","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737250","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737250","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737250","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307285","display_name":"Impact Fund","ror":"https://ror.org/00jb20j87"},{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320318398","display_name":"Ant Group","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412876956.pdf","grobid_xml":"https://content.openalex.org/works/W4412876956.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W2010440649","https://openalex.org/W2074995298","https://openalex.org/W2127201730","https://openalex.org/W2194775991","https://openalex.org/W2475334473","https://openalex.org/W2604379080","https://openalex.org/W2604382266","https://openalex.org/W2723293840","https://openalex.org/W2754517384","https://openalex.org/W2788295351","https://openalex.org/W2799544270","https://openalex.org/W2808422032","https://openalex.org/W2885929946","https://openalex.org/W2901874234","https://openalex.org/W2963654596","https://openalex.org/W2963841569","https://openalex.org/W2963895309","https://openalex.org/W2988150581","https://openalex.org/W2990138404","https://openalex.org/W3003416843","https://openalex.org/W3004983866","https://openalex.org/W3007094061","https://openalex.org/W3033324992","https://openalex.org/W3043826557","https://openalex.org/W3049342604","https://openalex.org/W3100789280","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3103141630","https://openalex.org/W3104669598","https://openalex.org/W3106431444","https://openalex.org/W3116873649","https://openalex.org/W3123348991","https://openalex.org/W3131301927","https://openalex.org/W3153252032","https://openalex.org/W3153687708","https://openalex.org/W3154055679","https://openalex.org/W3157410348","https://openalex.org/W3189576409","https://openalex.org/W3198517287","https://openalex.org/W3209943551","https://openalex.org/W4206497039","https://openalex.org/W4250331344","https://openalex.org/W4280602281","https://openalex.org/W4290874907","https://openalex.org/W4296591843","https://openalex.org/W4319653664","https://openalex.org/W4321479987","https://openalex.org/W4324312897","https://openalex.org/W4324323345","https://openalex.org/W4367047389","https://openalex.org/W4382203079","https://openalex.org/W4382239939","https://openalex.org/W4384641542","https://openalex.org/W4384655811","https://openalex.org/W4384891727","https://openalex.org/W4385565739","https://openalex.org/W4386721920","https://openalex.org/W4399554003","https://openalex.org/W4401857395","https://openalex.org/W4409149463","https://openalex.org/W6600007113","https://openalex.org/W6602847582"],"related_works":["https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W2150182025","https://openalex.org/W3092950680","https://openalex.org/W3197542405","https://openalex.org/W2056712470","https://openalex.org/W3125580266","https://openalex.org/W4288390103","https://openalex.org/W4317039510","https://openalex.org/W4225619808"],"abstract_inverted_index":{"Online":[0],"advertising":[1,34],"in":[2],"recommendation":[3,15,130],"platforms":[4],"has":[5],"gained":[6],"significant":[7],"attention,":[8],"with":[9],"a":[10,54,68,83],"predominant":[11],"focus":[12],"on":[13,150],"channel":[14,129],"and":[16,43,92,125,131,152],"budget":[17,45,132],"allocation":[18],"strategies.":[19],"However,":[20],"current":[21],"offline":[22,57,96,151],"reinforcement":[23],"learning":[24,121],"(RL)":[25],"methods":[26],"face":[27],"substantial":[28],"challenges":[29],"when":[30],"applied":[31],"to":[32,38,75,87,107,122],"sparse":[33],"scenarios,":[35],"primarily":[36],"due":[37],"severe":[39],"overestimation,":[40],"distributional":[41],"shifts,":[42],"overlooking":[44],"constraints.":[46],"To":[47],"address":[48],"these":[49,143],"issues,":[50],"we":[51,66,81],"propose":[52],"MTORL,":[53],"novel":[55],"multi-task":[56,120],"RL":[58,97],"model":[59],"that":[60],"targets":[61],"two":[62],"key":[63],"objectives.":[64],"First,":[65],"establish":[67],"Markov":[69],"Decision":[70],"Process":[71],"(MDP)":[72],"framework":[73,136],"specific":[74],"the":[76],"nuances":[77],"of":[78],"advertising.":[79,147],"Then,":[80],"develop":[82],"causal":[84,116],"state":[85],"encoder":[86],"capture":[88],"dynamic":[89],"user":[90,109],"interests":[91],"temporal":[93],"dependencies,":[94],"facilitating":[95],"through":[98],"conditional":[99],"sequence":[100,110],"modeling.":[101],"Causal":[102],"attention":[103],"mechanisms":[104],"are":[105],"introduced":[106],"enhance":[108],"representations":[111],"by":[112],"identifying":[113],"correlations":[114],"among":[115],"states.":[117],"We":[118],"employ":[119],"decode":[123],"actions":[124],"rewards,":[126],"simultaneously":[127],"addressing":[128],"allocation.":[133],"Notably,":[134],"our":[135],"includes":[137],"an":[138],"automated":[139],"system":[140],"for":[141],"integrating":[142],"tasks":[144],"into":[145],"online":[146,153,165],"Extensive":[148],"experiments":[149],"environments":[154],"demonstrate":[155],"MTORL's":[156],"superiority":[157],"over":[158],"state-of-the-art":[159],"methods.":[160],"The":[161],"code":[162],"is":[163],"available":[164],"at":[166],"https://github.com/Applied-Machine-Learning-Lab/MTORL.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
