{"id":"https://openalex.org/W2913167884","doi":"https://doi.org/10.1145/3289600.3291605","title":"Reinforcement Learning to Rank","display_name":"Reinforcement Learning to Rank","publication_year":2019,"publication_date":"2019-01-30","ids":{"openalex":"https://openalex.org/W2913167884","doi":"https://doi.org/10.1145/3289600.3291605","mag":"2913167884"},"language":"en","primary_location":{"id":"doi:10.1145/3289600.3291605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3289600.3291605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twelfth 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://dare.uva.nl/personal/pure/en/publications/reinforcement-learning-to-rank(0813c7ef-5dcc-43e3-81fd-6a8bde7f4bde).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031439294","display_name":"Maarten de Rijke","orcid":"https://orcid.org/0000-0002-1086-0202"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Maarten de Rijke","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5031439294"],"corresponding_institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":1.6464,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84580658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9628999829292297,"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":0.9628999829292297,"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/T10609","display_name":"Digital Marketing and Social Media","score":0.960099995136261,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.948199987411499,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.912726879119873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7572674751281738},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6632492542266846},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.6577743887901306},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6209484934806824},{"id":"https://openalex.org/keywords/mainstream","display_name":"Mainstream","score":0.5251510143280029},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5014691352844238},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4909215569496155},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.47317010164260864},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.4697442650794983},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.44988375902175903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43617942929267883},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37732285261154175},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3538225293159485},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.22522565722465515}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.912726879119873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7572674751281738},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6632492542266846},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6577743887901306},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6209484934806824},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.5251510143280029},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5014691352844238},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4909215569496155},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.47317010164260864},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.4697442650794983},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.44988375902175903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43617942929267883},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37732285261154175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3538225293159485},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.22522565722465515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3289600.3291605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3289600.3291605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire/0813c7ef-5dcc-43e3-81fd-6a8bde7f4bde","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/reinforcement-learning-to-rank(0813c7ef-5dcc-43e3-81fd-6a8bde7f4bde).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"de Rijke, M 2019, 'Reinforcement learning to rank', 12th ACM International Conference on Web Search and Data Mining, WSDM 2019, Melbourne, Australia, 11/02/19 - 15/02/19 pp. 5. https://doi.org/10.1145/3289600.3291605","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dare.uva.nl:publications/0813c7ef-5dcc-43e3-81fd-6a8bde7f4bde","is_oa":false,"landing_page_url":"http://hdl.handle.net/11245.1/0813c7ef-5dcc-43e3-81fd-6a8bde7f4bde","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/0813c7ef-5dcc-43e3-81fd-6a8bde7f4bde","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/reinforcement-learning-to-rank(0813c7ef-5dcc-43e3-81fd-6a8bde7f4bde).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"TITLE=12th ACM International Conference on Web Search and Data Mining, WSDM 2019","raw_type":"info:eu-repo/semantics/conferenceitemnotinproceedings"}],"best_oa_location":{"id":"pmh:uvapub:oai:dare.uva.nl:publications/0813c7ef-5dcc-43e3-81fd-6a8bde7f4bde","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/reinforcement-learning-to-rank(0813c7ef-5dcc-43e3-81fd-6a8bde7f4bde).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"TITLE=12th ACM International Conference on Web Search and Data Mining, WSDM 2019","raw_type":"info:eu-repo/semantics/conferenceitemnotinproceedings"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1583826057","https://openalex.org/W2377237701","https://openalex.org/W2360099860","https://openalex.org/W4323893170","https://openalex.org/W2352463596","https://openalex.org/W2772359885","https://openalex.org/W3011471740","https://openalex.org/W2884580467","https://openalex.org/W2544639518","https://openalex.org/W2572315477"],"abstract_inverted_index":{"Interactive":[0],"systems":[1,8],"such":[2],"as":[3,77],"search":[4,74,126,183],"engines":[5],"or":[6,37,75,98],"recommender":[7],"are":[9,28],"increasingly":[10],"moving":[11],"away":[12],"from":[13],"single-turn":[14,57],"exchanges":[15,21],"with":[16,130],"users.":[17],"Instead,":[18],"series":[19,79],"of":[20,73,80,122,133,136,145,164],"between":[22],"the":[23,26,39,44,56,93,106,137,142],"user":[24,67],"and":[25,115,127,148,170,172,184],"system":[27,40,94],"becoming":[29],"mainstream,":[30],"especially":[31],"when":[32,38],"users":[33],"have":[34],"complex":[35],"needs":[36],"struggles":[41],"to":[42,63,84,86,89,99,102,111],"understand":[43],"user's":[45],"intent.":[46],"Standard":[47],"machine":[48],"learning":[49,101,124,166,181],"has":[50],"helped":[51],"us":[52],"a":[53,78,131],"lot":[54],"in":[55],"paradigm,":[58],"where":[59],"we":[60,71,82],"use":[61,121],"it":[62],"predict:":[64],"intent,":[65],"relevance,":[66],"satisfaction,":[68],"etc.":[69],"When":[70],"think":[72],"recommendation":[76],"exchanges,":[81],"need":[83],"turn":[85],"bandit":[87],"algorithms":[88],"determine":[90,103],"which":[91],"action":[92,108,140],"should":[95],"take":[96],"next,":[97],"reinforcement":[100,123,165,180],"not":[104],"just":[105],"next":[107],"but":[109],"also":[110],"plan":[112],"future":[113,176],"actions":[114],"estimate":[116],"their":[117],"potential":[118,146],"pay-off.":[119],"The":[120],"for":[125,153,167,179,182],"recommendations":[128],"comes":[129],"number":[132,144],"challenges,":[134],"because":[135],"very":[138],"large":[139,143],"spaces,":[141],"contexts,":[147],"noisy":[149],"feedback":[150],"signals":[151],"characteristic":[152],"this":[154],"domain.":[155],"This":[156],"presentation":[157],"will":[158,173],"survey":[159],"some":[160],"recent":[161],"success":[162],"stories":[163],"search,":[168],"recommendation,":[169],"conversations;":[171],"identify":[174],"promising":[175],"research":[177],"directions":[178],"recommendation.":[185]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}