{"id":"https://openalex.org/W4386729683","doi":"https://doi.org/10.1145/3604915.3610641","title":"Integrating Offline Reinforcement Learning with Transformers for Sequential Recommendation","display_name":"Integrating Offline Reinforcement Learning with Transformers for Sequential Recommendation","publication_year":2023,"publication_date":"2023-09-14","ids":{"openalex":"https://openalex.org/W4386729683","doi":"https://doi.org/10.1145/3604915.3610641"},"language":"en","primary_location":{"id":"doi:10.1145/3604915.3610641","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604915.3610641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM Conference on Recommender Systems","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/A5053774944","display_name":"Xumei Xi","orcid":"https://orcid.org/0000-0002-1521-391X"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xumei Xi","raw_affiliation_strings":["School of Operations Research and Information Engineering, Cornell University, USA"],"affiliations":[{"raw_affiliation_string":"School of Operations Research and Information Engineering, Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103042882","display_name":"Yuke Zhao","orcid":"https://orcid.org/0009-0008-4620-8532"},"institutions":[{"id":"https://openalex.org/I1299907687","display_name":"Bloomberg (United States)","ror":"https://ror.org/02rdpzb15","country_code":"US","type":"company","lineage":["https://openalex.org/I1299907687"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuke Zhao","raw_affiliation_strings":["Bloomberg LP, USA"],"affiliations":[{"raw_affiliation_string":"Bloomberg LP, USA","institution_ids":["https://openalex.org/I1299907687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749063","display_name":"Quan Liu","orcid":"https://orcid.org/0009-0001-9770-4033"},"institutions":[{"id":"https://openalex.org/I1299907687","display_name":"Bloomberg (United States)","ror":"https://ror.org/02rdpzb15","country_code":"US","type":"company","lineage":["https://openalex.org/I1299907687"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quan Liu","raw_affiliation_strings":["Bloomberg, USA"],"affiliations":[{"raw_affiliation_string":"Bloomberg, USA","institution_ids":["https://openalex.org/I1299907687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018169421","display_name":"Liwen Ouyang","orcid":"https://orcid.org/0009-0007-6073-2763"},"institutions":[{"id":"https://openalex.org/I1299907687","display_name":"Bloomberg (United States)","ror":"https://ror.org/02rdpzb15","country_code":"US","type":"company","lineage":["https://openalex.org/I1299907687"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liwen Ouyang","raw_affiliation_strings":["Bloomberg, USA"],"affiliations":[{"raw_affiliation_string":"Bloomberg, USA","institution_ids":["https://openalex.org/I1299907687"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015956839","display_name":"Yang Wu","orcid":"https://orcid.org/0000-0002-9197-7794"},"institutions":[{"id":"https://openalex.org/I4210121988","display_name":"Film Independent","ror":"https://ror.org/036cy3843","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210121988"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Wu","raw_affiliation_strings":["Independent Researcher, USA"],"affiliations":[{"raw_affiliation_string":"Independent Researcher, USA","institution_ids":["https://openalex.org/I4210121988"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053774944"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":0.9133,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.80221926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973000288009644,"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/T10028","display_name":"Topic Modeling","score":0.9520999789237976,"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":0.8687698841094971},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8298001289367676},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7575826644897461},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.7141330242156982},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5491299629211426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5485140681266785},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.5328339338302612},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.4483092725276947},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.22232136130332947},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.10944095253944397},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09704411029815674}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8687698841094971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8298001289367676},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7575826644897461},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7141330242156982},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5491299629211426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5485140681266785},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.5328339338302612},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.4483092725276947},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.22232136130332947},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.10944095253944397},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09704411029815674},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3604915.3610641","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604915.3610641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM Conference on Recommender Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1997136459","https://openalex.org/W2017121215","https://openalex.org/W2054141820","https://openalex.org/W2783272285","https://openalex.org/W2788295351","https://openalex.org/W2893756876","https://openalex.org/W2963367478","https://openalex.org/W2981211936","https://openalex.org/W3005071803","https://openalex.org/W3040094401","https://openalex.org/W3102778384","https://openalex.org/W3116873649","https://openalex.org/W3118210634","https://openalex.org/W3194194466","https://openalex.org/W3199047808","https://openalex.org/W4360982002"],"related_works":["https://openalex.org/W4225619808","https://openalex.org/W4388926065","https://openalex.org/W4386160446","https://openalex.org/W4387545330","https://openalex.org/W4387293922","https://openalex.org/W4226221094","https://openalex.org/W4221145086","https://openalex.org/W4226042081","https://openalex.org/W92125585","https://openalex.org/W4284974072"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,8,24,34,52,72,76,149],"problem":[3],"of":[4,23,75,145,152],"sequential":[5,25,80],"recommendation,":[6],"where":[7],"current":[9],"recommendation":[10,18,128],"is":[11,103,124],"made":[12],"based":[13],"on":[14,88,95,116],"past":[15],"interactions.":[16],"This":[17],"task":[19],"requires":[20],"efficient":[21],"processing":[22],"data":[26],"and":[27,110,132,155],"aims":[28],"to":[29,78,83,105,136],"provide":[30],"recommendations":[31,144],"that":[32,59,86,102,121],"maximize":[33],"long-term":[35],"reward.":[36],"To":[37],"this":[38],"end,":[39],"we":[40,93,119],"train":[41],"a":[42,64,97,108],"farsighted":[43],"recommender":[44],"by":[45],"using":[46],"an":[47],"offline":[48,99],"RL":[49,100,154],"algorithm":[50,142],"with":[51],"policy":[53],"network":[54],"in":[55,107],"our":[56,122,141],"model":[57,70],"architecture":[58],"has":[60],"been":[61],"initialized":[62],"from":[63],"pre-trained":[65,69],"transformer":[66,77],"model.":[67],"The":[68],"leverages":[71],"superb":[73],"ability":[74],"process":[79],"information.":[81],"Compared":[82,135],"prior":[84],"works":[85],"rely":[87],"online":[89],"interaction":[90],"via":[91],"simulation,":[92],"focus":[94],"implementing":[96],"fully":[98],"framework":[101],"able":[104],"converge":[106],"fast":[109],"stable":[111],"way.":[112],"Through":[113],"extensive":[114],"experiments":[115],"public":[117],"datasets,":[118],"show":[120],"method":[123],"robust":[125],"across":[126],"various":[127],"regimes,":[129],"including":[130],"e-commerce":[131],"movie":[133],"suggestions.":[134],"state-of-the-art":[137],"supervised":[138],"learning":[139],"algorithms,":[140],"yields":[143],"higher":[146],"quality,":[147],"demonstrating":[148],"clear":[150],"advantage":[151],"combining":[153],"transformers.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}