{"id":"https://openalex.org/W4396843729","doi":"https://doi.org/10.1145/3589335.3648310","title":"User Response Modeling in Reinforcement Learning for Ads Allocation","display_name":"User Response Modeling in Reinforcement Learning for Ads Allocation","publication_year":2024,"publication_date":"2024-05-12","ids":{"openalex":"https://openalex.org/W4396843729","doi":"https://doi.org/10.1145/3589335.3648310"},"language":"en","primary_location":{"id":"doi:10.1145/3589335.3648310","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3648310","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3648310","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3648310","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022682143","display_name":"Zhiyuan Zhang","orcid":"https://orcid.org/0009-0003-2673-8169"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences & Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-2673-8169","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences & Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049454999","display_name":"Qichao Zhang","orcid":"https://orcid.org/0000-0001-9747-391X"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qichao Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences & Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9747-391X","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences & Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064929011","display_name":"Xiaoxu Wu","orcid":"https://orcid.org/0009-0000-8890-452X"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxu Wu","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-8890-452X","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088266717","display_name":"Xiaowen Shi","orcid":"https://orcid.org/0009-0003-2005-791X"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowen Shi","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-2005-791X","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036945708","display_name":"Guogang Liao","orcid":"https://orcid.org/0009-0002-6530-7102"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guogang Liao","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-6530-7102","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yongkang Wang","orcid":"https://orcid.org/0009-0003-5214-337X"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkang Wang","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-5214-337X","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000457098","display_name":"Xingxing Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingxing Wang","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5512-6442","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["University of Chinese Academy of Sciences & Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8218-9633","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences & Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11161","display_name":"Consumer Market Behavior and Pricing","score":0.9879000186920166,"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":0.9879000186920166,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9563999772071838,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9419000148773193,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7942569255828857},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7011266946792603},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4818076491355896},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.45483607053756714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2743109464645386},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16363248229026794}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7942569255828857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7011266946792603},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4818076491355896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45483607053756714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2743109464645386},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16363248229026794},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589335.3648310","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3648310","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3648310","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3589335.3648310","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3648310","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3648310","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8967284079","display_name":null,"funder_award_id":"No.62173325","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396843729.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2467077639","https://openalex.org/W2787933113","https://openalex.org/W2788295351","https://openalex.org/W2808227867","https://openalex.org/W2902572901","https://openalex.org/W2948345531","https://openalex.org/W2963367478","https://openalex.org/W2984582982","https://openalex.org/W3007094061","https://openalex.org/W3080386552","https://openalex.org/W3094280243","https://openalex.org/W3094577760","https://openalex.org/W3102778384","https://openalex.org/W3103141630","https://openalex.org/W3116249021","https://openalex.org/W3157410348","https://openalex.org/W3160355689","https://openalex.org/W3173331009","https://openalex.org/W3198517287","https://openalex.org/W4214717370","https://openalex.org/W4226395152","https://openalex.org/W4288269198","https://openalex.org/W4296604485","https://openalex.org/W4306317802","https://openalex.org/W4307774253","https://openalex.org/W4308080451","https://openalex.org/W4319792126","https://openalex.org/W4366377491"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"User":[0,85],"response":[1,51,91,123],"modeling":[2],"can":[3,160],"enhance":[4],"the":[5,13,56,67,95,102,105,114,121,185,215,225],"learning":[6,15],"of":[7,59,69,104,150],"user":[8,50,90,107,122,136],"representations":[9],"and":[10,29,128,139,190,219],"further":[11,162],"improve":[12],"reinforcement":[14],"(RL)":[16],"recommender":[17],"agent.":[18],"However,":[19],"as":[20],"users'":[21],"behaviors":[22],"are":[23,71],"influenced":[24],"by":[25],"their":[26],"long-term":[27,137],"preferences":[28,138],"short-term":[30,140],"stochastic":[31,129,141],"factors":[32],"(e.g.,":[33],"weather,":[34],"mood,":[35],"or":[36],"fashion":[37],"trends),":[38],"it":[39,61],"remains":[40],"challenging":[41],"for":[42,164],"previous":[43],"works":[44],"focusing":[45],"on":[46,109,179,224],"recurrent":[47],"neural":[48],"network-based":[49],"modeling.":[52],"Meanwhile,":[53],"due":[54],"to":[55,65,100,119,133,153,167,203],"dynamic":[57],"interests":[58],"users,":[60],"is":[62],"often":[63],"unrealistic":[64],"assume":[66],"dynamics":[68],"users":[70],"stationary.":[72],"Drawing":[73],"inspiration":[74],"from":[75,184],"opponent":[76],"modeling,":[77],"we":[78,112,145,175],"propose":[79],"a":[80,89,147,180,191,211],"novel":[81],"network":[82],"structure,":[83],"Deep":[84],"Q-Network":[86],"(DUQN),":[87],"incorporating":[88],"probabilistic":[92],"model":[93,159,209],"into":[94],"Q-learning":[96],"ads":[97],"allocation":[98],"strategy":[99],"capture":[101],"effect":[103],"non-stationary":[106],"policy":[108],"Q-values.":[110],"Moreover,":[111,207],"utilize":[113],"Recurrent":[115],"State-Space":[116],"Model":[117],"(RSSM)":[118],"develop":[120],"model,":[124],"which":[125],"includes":[126],"deterministic":[127],"components,":[130],"enabling":[131],"us":[132],"fully":[134,222],"consider":[135],"factors.":[142],"In":[143],"particular,":[144],"design":[146],"RetNet":[148],"version":[149],"RSSM":[151],"(R-RSSM)":[152],"support":[154],"parallel":[155],"computation.":[156],"The":[157],"R-RSSM":[158],"be":[161],"used":[163],"multi-step":[165],"predictions":[166],"enable":[168],"bootstrapping":[169],"over":[170],"multiple":[171],"steps":[172],"simultaneously.":[173],"Finally,":[174],"conduct":[176],"extensive":[177],"experiments":[178],"large-scale":[181],"offline":[182],"dataset":[183],"Meituan":[186,227],"food":[187],"delivery":[188],"platform":[189],"public":[192],"benchmark.":[193],"Experimental":[194],"results":[195],"show":[196],"that":[197],"our":[198,208],"method":[199],"yields":[200],"superior":[201],"performance":[202],"state-of-the-art":[204],"(SOTA)":[205],"baselines.":[206],"demonstrates":[210],"significant":[212],"improvement":[213],"in":[214],"online":[216],"A/B":[217],"test":[218],"has":[220],"been":[221],"deployed":[223],"industrial":[226],"platform,":[228],"serving":[229],"more":[230],"than":[231],"500":[232],"million":[233],"customers.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}