{"id":"https://openalex.org/W2612353123","doi":"https://doi.org/10.1007/978-1-4899-7687-1_244","title":"Efficient Exploration in Reinforcement Learning","display_name":"Efficient Exploration in Reinforcement Learning","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2612353123","doi":"https://doi.org/10.1007/978-1-4899-7687-1_244","mag":"2612353123"},"language":"en","primary_location":{"id":"doi:10.1007/978-1-4899-7687-1_244","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-1-4899-7687-1_244","pdf_url":null,"source":{"id":"https://openalex.org/S4306509369","display_name":"Encyclopedia of Machine Learning 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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Encyclopedia of Machine Learning and Data Mining","raw_type":"book-chapter"},"type":"book-chapter","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/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Langford","raw_affiliation_strings":["Microsoft Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, New York, NY, 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":2.67,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.92353062,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"389","last_page":"392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.5714707374572754},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4641493558883667},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4025081694126129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3684682846069336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2400101125240326},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09216222167015076}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5714707374572754},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4641493558883667},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4025081694126129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3684682846069336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2400101125240326},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09216222167015076}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-1-4899-7687-1_244","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-1-4899-7687-1_244","pdf_url":null,"source":{"id":"https://openalex.org/S4306509369","display_name":"Encyclopedia of Machine Learning 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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Encyclopedia of Machine Learning and Data Mining","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1996625075","https://openalex.org/W2129670787","https://openalex.org/W2531563875"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2089013912","https://openalex.org/W2076061571","https://openalex.org/W1987513656"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}