{"id":"https://openalex.org/W3034853385","doi":"https://doi.org/10.1145/3397271.3401147","title":"Self-Supervised Reinforcement Learning for Recommender Systems","display_name":"Self-Supervised Reinforcement Learning for Recommender Systems","publication_year":2020,"publication_date":"2020-07-25","ids":{"openalex":"https://openalex.org/W3034853385","doi":"https://doi.org/10.1145/3397271.3401147","mag":"3034853385"},"language":"en","primary_location":{"id":"doi:10.1145/3397271.3401147","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/231167/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100393241","display_name":"Xin Xin","orcid":"https://orcid.org/0000-0001-6116-9115"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Xin Xin","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082408006","display_name":"Alexandros Karatzoglou","orcid":"https://orcid.org/0000-0001-6063-9023"},"institutions":[{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexandros Karatzoglou","raw_affiliation_strings":["Google, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Google, London, United Kingdom","institution_ids":["https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015760420","display_name":"Ioannis Arapakis","orcid":"https://orcid.org/0000-0003-2528-6597"},"institutions":[{"id":"https://openalex.org/I4210134591","display_name":"Telefonica Research and Development","ror":"https://ror.org/03qgzzb04","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210097190","https://openalex.org/I4210134591"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ioannis Arapakis","raw_affiliation_strings":["Telefonica Research, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Telefonica Research, Barcelona, Spain","institution_ids":["https://openalex.org/I4210134591"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069702331","display_name":"Joemon M. Jose","orcid":"https://orcid.org/0000-0001-9228-1759"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joemon M. Jose","raw_affiliation_strings":["University of Glasgow, Galsgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Galsgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100393241"],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":22.2105,"has_fulltext":false,"cited_by_count":211,"citation_normalized_percentile":{"value":0.99652159,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"931","last_page":"940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9988999962806702,"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/T10603","display_name":"Smart Grid Energy Management","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8911168575286865},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.8531521558761597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8440196514129639},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.735983669757843},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5992549657821655},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4739641845226288},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.46946966648101807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4647158086299896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42986220121383667},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34598737955093384},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16168907284736633},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06717664003372192}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8911168575286865},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8531521558761597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8440196514129639},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.735983669757843},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5992549657821655},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4739641845226288},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.46946966648101807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4647158086299896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42986220121383667},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34598737955093384},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16168907284736633},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06717664003372192},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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":2,"locations":[{"id":"doi:10.1145/3397271.3401147","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:231167","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/231167/","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:231167","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/231167/","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1546409232","https://openalex.org/W1926826635","https://openalex.org/W2054141820","https://openalex.org/W2112420033","https://openalex.org/W2138108551","https://openalex.org/W2138909795","https://openalex.org/W2171279286","https://openalex.org/W2295739661","https://openalex.org/W2411690432","https://openalex.org/W2510184840","https://openalex.org/W2626454364","https://openalex.org/W2783272285","https://openalex.org/W2788295351","https://openalex.org/W2902040508","https://openalex.org/W2902572901","https://openalex.org/W2948345531","https://openalex.org/W2951625652","https://openalex.org/W2963367478","https://openalex.org/W2963403868","https://openalex.org/W2963654596","https://openalex.org/W2964108915","https://openalex.org/W2964296635","https://openalex.org/W3098867666","https://openalex.org/W3102619277","https://openalex.org/W3102778384","https://openalex.org/W3121197262","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4230197055","https://openalex.org/W4296749040","https://openalex.org/W4404605447","https://openalex.org/W621808327","https://openalex.org/W644007644","https://openalex.org/W4390273403","https://openalex.org/W2497198634","https://openalex.org/W3012257603","https://openalex.org/W1586784764","https://openalex.org/W4292264782"],"abstract_inverted_index":{"In":[0],"session-based":[1],"or":[2],"sequential":[3,39],"recommendation,":[4],"it":[5,69],"is":[6,48,58,70,101,106],"important":[7],"to":[8,34,59,73,82,85,88,109],"consider":[9],"a":[10,43,49,75,92],"number":[11],"of":[12,20,55,102,116],"factors":[13],"like":[14],"long-term":[15],"user":[16],"engagement,":[17],"multiple":[18],"types":[19],"user-item":[21],"interactions":[22,64],"such":[23],"as":[24,42],"clicks,":[25],"purchases":[26],"etc.":[27],"The":[28],"current":[29],"state-of-the-art":[30],"supervised":[31],"approaches":[32,57],"fail":[33],"model":[35],"them":[36],"appropriately.":[37],"Casting":[38],"recommendation":[40],"task":[41],"reinforcement":[44],"learning":[45,94],"(RL)":[46],"problem":[47],"promising":[50],"direction.":[51],"A":[52],"major":[53],"component":[54],"RL":[56],"train":[60,74],"the":[61,66,83,95,110],"agent":[62],"through":[63],"with":[65],"environment.":[67],"However,":[68],"often":[71],"problematic":[72],"recommender":[76],"in":[77],"an":[78],"on-line":[79],"fashion":[80],"due":[81,108],"requirement":[84],"expose":[86],"users":[87],"irrelevant":[89],"recommendations.":[90],"As":[91],"result,":[93],"policy":[96],"from":[97],"logged":[98],"implicit":[99],"feedback":[100],"vital":[103],"importance,":[104],"which":[105],"challenging":[107],"pure":[111],"off-policy":[112],"setting":[113],"and":[114],"lack":[115],"negative":[117],"rewards":[118],"(feedback).":[119]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":53},{"year":2023,"cited_by_count":52},{"year":2022,"cited_by_count":33},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}
