{"id":"https://openalex.org/W4319239745","doi":"https://doi.org/10.1007/978-1-4899-7687-1_16","title":"Autonomous Helicopter Flight Using Reinforcement Learning","display_name":"Autonomous Helicopter Flight Using Reinforcement Learning","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W4319239745","doi":"https://doi.org/10.1007/978-1-4899-7687-1_16"},"language":"en","primary_location":{"id":"doi:10.1007/978-1-4899-7687-1_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-1-4899-7687-1_16","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":"reference-entry","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/A5103153292","display_name":"Adam Coates","orcid":"https://orcid.org/0000-0002-4004-1603"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Adam Coates","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":["EECS Department, UC Berkeley, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EECS Department, UC Berkeley, Stanford, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112456378","display_name":"Andrew Y. Ng","orcid":"https://orcid.org/0000-0001-5547-3196"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Y. Ng","raw_affiliation_strings":["Computer Science Department, Stanford University, Stanford, CA, USA","Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103153292"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9986000061035156,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.986299991607666,"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/aeronautics","display_name":"Aeronautics","score":0.6566016674041748},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6301882863044739},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43329358100891113},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4296364188194275},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.35114917159080505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33354777097702026},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3021412789821625},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07113519310951233}],"concepts":[{"id":"https://openalex.org/C178802073","wikidata":"https://www.wikidata.org/wiki/Q8421","display_name":"Aeronautics","level":1,"score":0.6566016674041748},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6301882863044739},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43329358100891113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4296364188194275},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.35114917159080505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33354777097702026},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3021412789821625},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07113519310951233}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-1-4899-7687-1_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-1-4899-7687-1_16","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":19,"referenced_works":["https://openalex.org/W177930832","https://openalex.org/W246617311","https://openalex.org/W1556500232","https://openalex.org/W1559856396","https://openalex.org/W1583837637","https://openalex.org/W1996625075","https://openalex.org/W1999874108","https://openalex.org/W2012302913","https://openalex.org/W2025752438","https://openalex.org/W2049633694","https://openalex.org/W2071069134","https://openalex.org/W2103608534","https://openalex.org/W2130105540","https://openalex.org/W2132602063","https://openalex.org/W2135043890","https://openalex.org/W2158598687","https://openalex.org/W2169209873","https://openalex.org/W2171074980","https://openalex.org/W2489939061"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}