{"id":"https://openalex.org/W3211540990","doi":"https://doi.org/10.1145/3488560.3498494","title":"Supervised Advantage Actor-Critic for Recommender Systems","display_name":"Supervised Advantage Actor-Critic for Recommender Systems","publication_year":2022,"publication_date":"2022-02-11","ids":{"openalex":"https://openalex.org/W3211540990","doi":"https://doi.org/10.1145/3488560.3498494","mag":"3211540990"},"language":"en","primary_location":{"id":"doi:10.1145/3488560.3498494","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3488560.3498494","pdf_url":null,"source":{"id":"https://openalex.org/S4363608885","display_name":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/257042/2/257042.pdf","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/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Xin","raw_affiliation_strings":["Shandong University, Qingdao City, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao City, China","institution_ids":["https://openalex.org/I154099455"]}]},{"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 Research, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Google Research, 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, Glasgow, Scotland Uk"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, Scotland Uk","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100393241"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":12.1317,"has_fulltext":true,"cited_by_count":48,"citation_normalized_percentile":{"value":0.99312169,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1186","last_page":"1196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998000264167786,"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":0.9998000264167786,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9955999851226807,"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":0.8107517957687378},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7874156832695007},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.7417963743209839},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.7368183732032776},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.5753519535064697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5716558694839478},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5035743117332458},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49060311913490295},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4849138855934143},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13503801822662354},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.08812877535820007},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.0751703679561615}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8107517957687378},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7874156832695007},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7417963743209839},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.7368183732032776},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.5753519535064697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5716558694839478},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5035743117332458},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49060311913490295},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4849138855934143},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13503801822662354},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.08812877535820007},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0751703679561615},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3488560.3498494","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3488560.3498494","pdf_url":null,"source":{"id":"https://openalex.org/S4363608885","display_name":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:257042","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/43969.html>,","pdf_url":"https://eprints.gla.ac.uk/257042/2/257042.pdf","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:257042","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/43969.html>,","pdf_url":"https://eprints.gla.ac.uk/257042/2/257042.pdf","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":[{"score":0.4300000071525574,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1909507932","display_name":null,"funder_award_id":"62106105","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2003888216","display_name":null,"funder_award_id":"ZR2021QF129","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G394483262","display_name":null,"funder_award_id":"61972234","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4278653462","display_name":null,"funder_award_id":"61902219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G69085316","display_name":null,"funder_award_id":"62102234","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8077820885","display_name":null,"funder_award_id":"06105","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8672301212","display_name":null,"funder_award_id":"62072279","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320311026","display_name":"Shandong University","ror":"https://ror.org/0207yh398"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3211540990.pdf","grobid_xml":"https://content.openalex.org/works/W3211540990.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1926826635","https://openalex.org/W1977655452","https://openalex.org/W2069870183","https://openalex.org/W2099471712","https://openalex.org/W2101409192","https://openalex.org/W2112420033","https://openalex.org/W2125442594","https://openalex.org/W2138108551","https://openalex.org/W2140310134","https://openalex.org/W2145339207","https://openalex.org/W2171279286","https://openalex.org/W2257979135","https://openalex.org/W2262817822","https://openalex.org/W2295739661","https://openalex.org/W2783272285","https://openalex.org/W2788295351","https://openalex.org/W2802726207","https://openalex.org/W2886144305","https://openalex.org/W2886601525","https://openalex.org/W2902040508","https://openalex.org/W2902572901","https://openalex.org/W2911607485","https://openalex.org/W2946327583","https://openalex.org/W2946400218","https://openalex.org/W2948345531","https://openalex.org/W2950577311","https://openalex.org/W2951403958","https://openalex.org/W2951625652","https://openalex.org/W2963014947","https://openalex.org/W2963277051","https://openalex.org/W2963367478","https://openalex.org/W2963403868","https://openalex.org/W2963654596","https://openalex.org/W2963674921","https://openalex.org/W2963704132","https://openalex.org/W2964108915","https://openalex.org/W2964157711","https://openalex.org/W2964296635","https://openalex.org/W2972510393","https://openalex.org/W2975999915","https://openalex.org/W2980433389","https://openalex.org/W3034853385","https://openalex.org/W3102778384","https://openalex.org/W3115293622","https://openalex.org/W3209145439","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2060561905","https://openalex.org/W1417711376","https://openalex.org/W2032260263","https://openalex.org/W1986883493","https://openalex.org/W2469862403","https://openalex.org/W2166378262","https://openalex.org/W2035891203","https://openalex.org/W4379524643","https://openalex.org/W2011027677","https://openalex.org/W2367807705"],"abstract_inverted_index":{"Casting":[0],"session-based":[1],"or":[2],"sequential":[3,68],"recommendation":[4],"as":[5],"reinforcement":[6],"learning":[7],"(RL)":[8],"through":[9],"reward":[10,51,95],"signals":[11],"is":[12,36],"a":[13,108],"promising":[14],"research":[15],"direction":[16],"towards":[17],"recommender":[18],"systems":[19],"(RS)":[20],"that":[21],"maximize":[22],"cumulative":[23],"profits.":[24],"However,":[25],"the":[26,33,78,91,98,104],"direct":[27],"use":[28],"of":[29,49,80,93,107],"RL":[30,54,65],"algorithms":[31],"in":[32],"RS":[34,57],"setting":[35],"impractical":[37],"due":[38,89],"to":[39,59,83,90],"challenges":[40,62],"like":[41],"off-policy":[42],"training,":[43],"huge":[44],"action":[45],"spaces":[46],"and":[47,66],"lack":[48,92],"sufficient":[50],"signals.":[52,96],"Recent":[53],"approaches":[55],"for":[56],"attempt":[58],"tackle":[60],"these":[61],"by":[63],"combining":[64],"(self-)supervised":[67],"learning,":[69],"but":[70],"still":[71],"suffer":[72],"from":[73],"certain":[74],"limitations.":[75],"For":[76],"example,":[77],"estimation":[79],"Q-values":[81,99],"tends":[82],"be":[84],"biased":[85],"toward":[86],"positive":[87],"values":[88],"negative":[94],"Moreover,":[97],"also":[100],"depend":[101],"heavily":[102],"on":[103],"specific":[105],"timestamp":[106],"sequence.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}