{"id":"https://openalex.org/W4400525872","doi":"https://doi.org/10.1145/3626772.3657714","title":"Reinforcing Long-Term Performance in Recommender Systems with User-Oriented Exploration Policy","display_name":"Reinforcing Long-Term Performance in Recommender Systems with User-Oriented Exploration Policy","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400525872","doi":"https://doi.org/10.1145/3626772.3657714"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657714","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3657714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/A5103144692","display_name":"Changshuo Zhang","orcid":"https://orcid.org/0009-0001-8481-9421"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changshuo Zhang","raw_affiliation_strings":["Gaoling School of AI, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8481-9421","affiliations":[{"raw_affiliation_string":"Gaoling School of AI, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073327702","display_name":"Sirui Chen","orcid":"https://orcid.org/0000-0001-7740-508X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sirui Chen","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, USA"],"raw_orcid":"https://orcid.org/0000-0001-7740-508X","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320847","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0001-7397-5632"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Zhang","raw_affiliation_strings":["Gaoling School of AI, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7397-5632","affiliations":[{"raw_affiliation_string":"Gaoling School of AI, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075518954","display_name":"Sunhao Dai","orcid":"https://orcid.org/0009-0002-7549-0860"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sunhao Dai","raw_affiliation_strings":["Gaoling School of AI, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-7549-0860","affiliations":[{"raw_affiliation_string":"Gaoling School of AI, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016774863","display_name":"Weijie Yu","orcid":"https://orcid.org/0000-0002-5676-4339"},"institutions":[{"id":"https://openalex.org/I146563203","display_name":"University of International Business and Economics","ror":"https://ror.org/05khqpb71","country_code":"CN","type":"education","lineage":["https://openalex.org/I146563203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijie Yu","raw_affiliation_strings":["School of Information Technology and Management, University of International Business and Economics, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5676-4339","affiliations":[{"raw_affiliation_string":"School of Information Technology and Management, University of International Business and Economics, Beijing, China","institution_ids":["https://openalex.org/I146563203"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020766468","display_name":"Jun Xu","orcid":"https://orcid.org/0000-0001-7170-111X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xu","raw_affiliation_strings":["Gaoling School of AI, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7170-111X","affiliations":[{"raw_affiliation_string":"Gaoling School of AI, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.195,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.95617232,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1850","last_page":"1860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9984999895095825,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9860000014305115,"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/recommender-system","display_name":"Recommender system","score":0.8355892896652222},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.8257114887237549},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7777563333511353},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42012137174606323},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33271512389183044}],"concepts":[{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8355892896652222},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.8257114887237549},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777563333511353},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42012137174606323},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33271512389183044},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626772.3657714","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3657714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1777256224","display_name":null,"funder_award_id":"62376275,62377044","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G1934805195","display_name":null,"funder_award_id":"2022ZD0114802","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1976659148","https://openalex.org/W2112420033","https://openalex.org/W2138909795","https://openalex.org/W2187089797","https://openalex.org/W2746553466","https://openalex.org/W2765302304","https://openalex.org/W2787933113","https://openalex.org/W2799544270","https://openalex.org/W2810397803","https://openalex.org/W2877093712","https://openalex.org/W2902572901","https://openalex.org/W2963367478","https://openalex.org/W2964108915","https://openalex.org/W2973171206","https://openalex.org/W2978943496","https://openalex.org/W2997528551","https://openalex.org/W3004082694","https://openalex.org/W3033324992","https://openalex.org/W3034503922","https://openalex.org/W3102899483","https://openalex.org/W3114652457","https://openalex.org/W3155368131","https://openalex.org/W3155850838","https://openalex.org/W3183218305","https://openalex.org/W3200556911","https://openalex.org/W3201286590","https://openalex.org/W4280522538","https://openalex.org/W4284974072","https://openalex.org/W4290927796","https://openalex.org/W4293585414","https://openalex.org/W4319792126","https://openalex.org/W4372347502","https://openalex.org/W4380136520","https://openalex.org/W4386728944","https://openalex.org/W4387846685","https://openalex.org/W6630221451"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","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/W4317039510"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3],"gained":[4],"popularity":[5],"in":[6,183],"recommender":[7,20],"systems":[8,21],"for":[9,200],"improving":[10],"long-term":[11,68,186],"performance":[12,199],"by":[13],"effectively":[14],"exploring":[15],"users'":[16],"interests.":[17],"However,":[18],"modern":[19],"face":[22],"the":[23,150,172,192],"challenge":[24],"of":[25,32,106,129,174,185,194],"different":[26,46,116],"user":[27,69,89,113,141],"behavioral":[28],"patterns":[29],"among":[30,88,206],"millions":[31],"items,":[33],"making":[34],"exploration":[35,47,60,87,137,151],"more":[36],"difficult.":[37],"For":[38],"example,":[39],"users":[40,202],"with":[41,115],"varying":[42,103],"activity":[43,117],"levels":[44,105],"require":[45],"intensities.":[48],"Unfortunately,":[49],"previous":[50],"studies":[51],"often":[52],"overlook":[53],"this":[54,120],"aspect":[55],"and":[56,135,147,161,203],"apply":[57],"a":[58,81,94,123,127,156,162],"uniform":[59],"strategy":[61],"to":[62,133],"all":[63,180],"users,":[64,111],"which":[65],"ultimately":[66],"hampers":[67],"experiences.":[70],"To":[71,143],"tackle":[72],"these":[73],"challenges,":[74],"we":[75,125,153],"propose":[76],"User-Oriented":[77],"Exploration":[78],"Policy":[79],"(UOEP),":[80],"novel":[82],"approach":[83],"that":[84,97],"enables":[85],"fine-grained":[86,136],"groups.":[90,142],"We":[91],"first":[92],"construct":[93],"distributional":[95],"critic":[96,121],"allows":[98],"policy":[99],"optimization":[100],"based":[101],"on":[102,167],"quantile":[104],"cumulative":[107],"reward":[108],"feedback":[109],"from":[110],"representing":[112],"groups":[114],"levels.":[118],"Using":[119],"as":[122,177],"guide,":[124],"design":[126],"population":[128],"distinct":[130],"actors":[131],"dedicated":[132],"effective":[134],"within":[138],"their":[139],"respective":[140],"simultaneously":[144],"enhance":[145],"diversity":[146,158],"stability":[148],"during":[149],"process,":[152],"also":[154],"introduce":[155],"population-level":[157],"regularization":[159],"term":[160],"supervision":[163],"module.":[164],"Experimental":[165],"results":[166],"public":[168],"recommendation":[169],"datasets":[170],"validate":[171],"effectiveness":[173],"our":[175,195],"approach,":[176,196],"it":[178],"outperforms":[179],"other":[181],"baselines":[182],"terms":[184],"performance.":[187],"Moreover,":[188],"further":[189],"analyses":[190],"reveal":[191],"benefits":[193],"including":[197],"improved":[198],"low-activity":[201],"increased":[204],"fairness":[205],"users.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}