{"id":"https://openalex.org/W2948345531","doi":"https://doi.org/10.24963/ijcai.2019/360","title":"SlateQ: A Tractable Decomposition for Reinforcement Learning with Recommendation Sets","display_name":"SlateQ: A Tractable Decomposition for Reinforcement Learning with Recommendation Sets","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2948345531","doi":"https://doi.org/10.24963/ijcai.2019/360","mag":"2948345531"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/360","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/360","pdf_url":"https://www.ijcai.org/proceedings/2019/0360.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0360.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013936779","display_name":"Eugene Ie","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Ie","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112456155","display_name":"Vihan Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vihan Jain","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028389743","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0002-2407-5985"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032114961","display_name":"Sanmit Narvekar","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanmit Narvekar","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065713450","display_name":"Ritesh Agarwal","orcid":"https://orcid.org/0000-0002-1289-4334"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ritesh Agarwal","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449415","display_name":"Rui Wu","orcid":"https://orcid.org/0000-0003-0941-2688"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Wu","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054880622","display_name":"Heng-Tze Cheng","orcid":"https://orcid.org/0009-0007-3845-8796"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng-Tze Cheng","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085084822","display_name":"Tushar Chandra","orcid":"https://orcid.org/0009-0006-1475-3427"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tushar Chandra","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036934218","display_name":"Craig Boutilier","orcid":"https://orcid.org/0000-0001-9330-4545"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Craig Boutilier","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.3199,"has_fulltext":false,"cited_by_count":113,"citation_normalized_percentile":{"value":0.98592657,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2592","last_page":"2599"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9976999759674072,"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":0.9921000003814697,"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":0.9108462333679199},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.7732425928115845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7609673738479614},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.741422712802887},{"id":"https://openalex.org/keywords/slates","display_name":"SLATES","score":0.7235302329063416},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.6046173572540283},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5487077236175537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5145365595817566},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4570259749889374},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4549751281738281},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4534301161766052},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.41216135025024414},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4100702404975891},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3960399031639099},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3024635314941406},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13176769018173218},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10673683881759644},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10041484236717224}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9108462333679199},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7732425928115845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7609673738479614},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.741422712802887},{"id":"https://openalex.org/C2780103627","wikidata":"https://www.wikidata.org/wiki/Q7390747","display_name":"SLATES","level":2,"score":0.7235302329063416},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.6046173572540283},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5487077236175537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5145365595817566},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4570259749889374},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4549751281738281},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4534301161766052},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.41216135025024414},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4100702404975891},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3960399031639099},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3024635314941406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13176769018173218},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10673683881759644},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10041484236717224},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/360","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/360","pdf_url":"https://www.ijcai.org/proceedings/2019/0360.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/360","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/360","pdf_url":"https://www.ijcai.org/proceedings/2019/0360.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2948345531.pdf","grobid_xml":"https://content.openalex.org/works/W2948345531.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W245387374","https://openalex.org/W1550812296","https://openalex.org/W1992549066","https://openalex.org/W2047221353","https://openalex.org/W2100752967","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2128668628","https://openalex.org/W2135263912","https://openalex.org/W2137028279","https://openalex.org/W2137245235","https://openalex.org/W2138108551","https://openalex.org/W2142144955","https://openalex.org/W2143996311","https://openalex.org/W2146412174","https://openalex.org/W2156577211","https://openalex.org/W2171279286","https://openalex.org/W2189395077","https://openalex.org/W2475334473","https://openalex.org/W2512971201","https://openalex.org/W2583674722","https://openalex.org/W2615790994","https://openalex.org/W2767696711","https://openalex.org/W2783573456","https://openalex.org/W2799544270","https://openalex.org/W2898621204","https://openalex.org/W2902572901","https://openalex.org/W2905342215","https://openalex.org/W2949183401","https://openalex.org/W2950332743","https://openalex.org/W3118655244","https://openalex.org/W4213378752","https://openalex.org/W4214717370","https://openalex.org/W4241676240","https://openalex.org/W4288346394","https://openalex.org/W4293653493","https://openalex.org/W4298023569"],"related_works":["https://openalex.org/W1971536134","https://openalex.org/W2165707846","https://openalex.org/W4239945603","https://openalex.org/W3034798441","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W4401051025","https://openalex.org/W2065296176","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"methods":[2,90],"for":[3,8],"recommender":[4],"systems":[5],"optimize":[6],"recommendations":[7],"long-term":[9,69],"user":[10,28,62],"engagement.":[11],"However,":[12],"since":[13],"users":[14],"are":[15,30],"often":[16],"presented":[17],"with":[18,34,56],"slates":[19],"of":[20,37,47,72,82,99],"multiple":[21],"items---which":[22],"may":[23],"have":[24],"interacting":[25],"effects":[26],"on":[27,61,102],"choice---methods":[29],"required":[31],"to":[32],"deal":[33],"the":[35,38,68,95],"combinatorics":[36],"RL":[39,54],"action":[40],"space.":[41],"We":[42,87],"develop":[43],"SlateQ,":[44],"a":[45,73,79],"decomposition":[46],"value-based":[48],"temporal-difference":[49],"and":[50,93,97],"Q-learning":[51],"that":[52,67],"renders":[53],"tractable":[55,80],"slates.":[57],"Under":[58],"mild":[59],"assumptions":[60],"choice":[63],"behavior,":[64],"we":[65],"show":[66],"value":[70],"(LTV)":[71],"slate":[74],"can":[75],"be":[76],"decomposed":[77,100],"into":[78],"function":[81],"its":[83],"component":[84],"item-wise":[85],"LTVs.":[86],"demonstrate":[88],"our":[89],"in":[91],"simulation,":[92],"validate":[94],"scalability":[96],"effectiveness":[98],"TD-learning":[101],"YouTube.":[103]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}