{"id":"https://openalex.org/W2783109451","doi":"https://doi.org/10.1109/bigdata.2017.8257902","title":"Contextual reinforcement learning","display_name":"Contextual reinforcement learning","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2783109451","doi":"https://doi.org/10.1109/bigdata.2017.8257902","mag":"2783109451"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2017.8257902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8257902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","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/A5005003250","display_name":"John Langford","orcid":"https://orcid.org/0000-0002-9811-3550"},"institutions":[{"id":"https://openalex.org/I4401726785","display_name":"Microsoft Research New York City (United States)","ror":"https://ror.org/056zprp28","country_code":null,"type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Langford","raw_affiliation_strings":["Microsoft Research New York, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research New York, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5005003250"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.23730169,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"3"},"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":0.9947999715805054,"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":0.993399977684021,"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":0.9078196287155151},{"id":"https://openalex.org/keywords/aka","display_name":"AKA","score":0.8586353063583374},{"id":"https://openalex.org/keywords/contextual-inquiry","display_name":"Contextual inquiry","score":0.7089606523513794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7027725577354431},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6289210319519043},{"id":"https://openalex.org/keywords/contextual-design","display_name":"Contextual design","score":0.5057723522186279},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5052705407142639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45708250999450684},{"id":"https://openalex.org/keywords/contextual-learning","display_name":"Contextual learning","score":0.4284895658493042},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39928269386291504},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.152476966381073},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10659536719322205},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.10393857955932617}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9078196287155151},{"id":"https://openalex.org/C121158502","wikidata":"https://www.wikidata.org/wiki/Q4652161","display_name":"AKA","level":2,"score":0.8586353063583374},{"id":"https://openalex.org/C135355979","wikidata":"https://www.wikidata.org/wiki/Q5165193","display_name":"Contextual inquiry","level":2,"score":0.7089606523513794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7027725577354431},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6289210319519043},{"id":"https://openalex.org/C71611378","wikidata":"https://www.wikidata.org/wiki/Q5165191","display_name":"Contextual design","level":3,"score":0.5057723522186279},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5052705407142639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45708250999450684},{"id":"https://openalex.org/C2777541608","wikidata":"https://www.wikidata.org/wiki/Q5165194","display_name":"Contextual learning","level":2,"score":0.4284895658493042},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39928269386291504},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.152476966381073},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10659536719322205},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.10393857955932617},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2017.8257902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8257902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2039522160","https://openalex.org/W2519411794"],"related_works":["https://openalex.org/W4298884284","https://openalex.org/W4214664259","https://openalex.org/W2783109451","https://openalex.org/W3202773780","https://openalex.org/W3002821385","https://openalex.org/W2134552108","https://openalex.org/W2787024441","https://openalex.org/W3138992458","https://openalex.org/W2024505744","https://openalex.org/W1487055405"],"abstract_inverted_index":{"I":[0],"will":[1],"discuss":[2],"a":[3,55],"decade":[4],"long":[5],"research":[6,20],"project":[7,21],"to":[8,29],"create":[9],"the":[10,50],"foundations":[11],"of":[12,38],"reinforcement":[13],"learning":[14],"with":[15],"context":[16],"(aka":[17],"features).":[18],"This":[19],"has":[22],"multiple":[23],"threads":[24],"including":[25],"Contextual":[26,32],"Bandits,":[27],"Learning":[28],"Search,":[30],"and":[31],"Decision":[33],"Processes.":[34],"The":[35],"most":[36],"mature":[37,52],"these":[39],"(Contextual":[40],"Bandits)":[41],"is":[42,54],"now":[43],"driving":[44],"many":[45],"real-world":[46],"RL":[47],"applications":[48],"while":[49],"least":[51],"(CDPs)":[53],"fascinating":[56],"theoretician's":[57],"toy.":[58]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}