{"id":"https://openalex.org/W4403221196","doi":"https://doi.org/10.1145/3640457.3691698","title":"Multi-Preview Recommendation via Reinforcement Learning","display_name":"Multi-Preview Recommendation via Reinforcement Learning","publication_year":2024,"publication_date":"2024-10-08","ids":{"openalex":"https://openalex.org/W4403221196","doi":"https://doi.org/10.1145/3640457.3691698"},"language":"en","primary_location":{"id":"doi:10.1145/3640457.3691698","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3691698","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3691698","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3691698","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102564692","display_name":"Yang Xu","orcid":"https://orcid.org/0009-0008-6473-8529"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yang Xu","raw_affiliation_strings":["Department of Statistics, North Carolina State University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004962312","display_name":"Kuan-Ting Lai","orcid":"https://orcid.org/0009-0002-3576-0512"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuan-Ting Lai","raw_affiliation_strings":["Feeds & Verticals, Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Feeds & Verticals, Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063102924","display_name":"Pengcheng Xiong","orcid":"https://orcid.org/0000-0003-4707-1634"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengcheng Xiong","raw_affiliation_strings":["Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070394287","display_name":"Zhong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong Wu","raw_affiliation_strings":["Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102564692"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21546723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1180","last_page":"1183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9955000281333923,"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":0.9955000281333923,"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":0.995199978351593,"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":0.9937999844551086,"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":0.7885526418685913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.725700855255127},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44686877727508545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3725582957267761},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33360838890075684},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12608006596565247}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7885526418685913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.725700855255127},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44686877727508545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3725582957267761},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33360838890075684},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12608006596565247},{"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:10.1145/3640457.3691698","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3691698","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3691698","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th ACM Conference on Recommender Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3640457.3691698","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3691698","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3691698","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403221196.pdf"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W3081235889","https://openalex.org/W3094001213","https://openalex.org/W3170112077","https://openalex.org/W4206497039","https://openalex.org/W4283456704"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Preview":[0],"recommendations":[1,43],"serve":[2],"as":[3],"a":[4,59],"crucial":[5],"shortcut":[6],"for":[7,41,90],"attracting":[8],"users\u2019":[9],"attention":[10],"on":[11],"various":[12],"systems,":[13],"platforms,":[14],"and":[15,27,68,93,117],"webpages,":[16],"significantly":[17],"boosting":[18],"user":[19,74],"engagement.":[20],"However,":[21],"the":[22,28,79,109],"variability":[23],"of":[24,30,111],"preview":[25,31],"types":[26],"flexibility":[29],"duration":[32,69],"make":[33],"it":[34],"challenging":[35],"to":[36,105],"use":[37],"an":[38,52],"integrated":[39],"framework":[40],"multi-preview":[42,66],"under":[44],"resource":[45],"constraints.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"present":[51],"approach":[53,113],"that":[54],"incorporates":[55],"constrained":[56],"Q-learning":[57],"into":[58],"notification":[60],"recommendation":[61],"system,":[62],"effectively":[63],"handling":[64],"both":[65],"ranking":[67],"orchestration":[70],"by":[71],"targeting":[72],"long-term":[73],"retention.":[75],"Our":[76],"method":[77],"bridges":[78],"gap":[80],"between":[81],"combinatorial":[82],"reinforcement":[83],"learning,":[84],"which":[85],"often":[86],"remains":[87],"too":[88],"theoretical":[89],"practical":[91],"use,":[92],"segmented":[94],"modules":[95],"in":[96],"production,":[97],"where":[98],"model":[99],"performance":[100],"is":[101],"typically":[102],"compromised":[103],"due":[104],"over-simplification.":[106],"We":[107],"demonstrate":[108],"superiority":[110],"our":[112],"through":[114],"off-policy":[115],"evaluation":[116],"online":[118],"A/B":[119],"testing":[120],"using":[121],"Microsoft":[122],"data.":[123]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}