{"id":"https://openalex.org/W2108734173","doi":null,"title":"Autonomous Helicopter Flight via Reinforcement Learning","display_name":"Autonomous Helicopter Flight via Reinforcement Learning","publication_year":2003,"publication_date":"2003-12-09","ids":{"openalex":"https://openalex.org/W2108734173","mag":"2108734173"},"language":"en","primary_location":{"id":"mag:2108734173","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/2003/file/b427426b8acd2c2e53827970f2c2f526-Paper.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5057227319","display_name":"H. J. Kim","orcid":null,"observed_orcids":[]},"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":"H. J. Kim","raw_affiliation_strings":["Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049812527","display_name":"Michael I. Jordan","orcid":"https://orcid.org/0000-0001-8935-817X","observed_orcids":["https://orcid.org/0000-0001-8935-817X","https://orcid.org/0000-0002-2177-0405","https://orcid.org/0000-0002-5776-2626"]},"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":"Michael I. Jordan","raw_affiliation_strings":["University of California: Berkeley, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California: Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062722286","display_name":"Shankar Sastry","orcid":"https://orcid.org/0009-0000-9021-7235","observed_orcids":["https://orcid.org/0009-0000-9021-7235","https://orcid.org/0000-0003-1300-1574"]},"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":"S. Shankar Sastry","raw_affiliation_strings":["University of California: Berkeley, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California: Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102617494","display_name":"Andrew Y. Ng","orcid":"https://orcid.org/0000-0001-5547-3196","observed_orcids":["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":["Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.2848,"has_fulltext":false,"cited_by_count":290,"citation_normalized_percentile":{"value":0.9714467,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"16","issue":null,"first_page":"799","last_page":"806"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T12125","display_name":"Aerospace and Aviation Technology","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":9.999999747378752e-05,"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":0.9129999876022339},{"id":"https://openalex.org/keywords/helicopter-dynamics-modeling","display_name":"helicopter dynamics modeling","score":0.9039999842643738},{"id":"https://openalex.org/keywords/nonlinear-stochastic-dynamics","display_name":"nonlinear stochastic dynamics","score":0.7020000219345093},{"id":"https://openalex.org/keywords/hover-control","display_name":"hover control","score":0.8859999775886536},{"id":"https://openalex.org/keywords/flight-maneuvers","display_name":"flight maneuvers","score":0.6430000066757202},{"id":"https://openalex.org/keywords/model-based-learning","display_name":"model-based learning","score":0.4819999933242798}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8491462469100952},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5733810067176819},{"id":"https://openalex.org/C206923515","wikidata":"https://www.wikidata.org/wiki/Q5459269","display_name":"Flight dynamics","level":3,"score":0.5606520175933838},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.46391215920448303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43450090289115906},{"id":"https://openalex.org/C2984755018","wikidata":"https://www.wikidata.org/wiki/Q17118374","display_name":"Nonlinear model","level":3,"score":0.42029285430908203},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.401994526386261},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3465033173561096},{"id":"https://openalex.org/C13393347","wikidata":"https://www.wikidata.org/wiki/Q8424","display_name":"Aerodynamics","level":2,"score":0.2717441916465759},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.2413145899772644},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06020796298980713},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2108734173","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/2003/file/b427426b8acd2c2e53827970f2c2f526-Paper.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W142858861","https://openalex.org/W1601974704","https://openalex.org/W1689445748","https://openalex.org/W1777239053","https://openalex.org/W1994616650","https://openalex.org/W2009797711","https://openalex.org/W2024081693","https://openalex.org/W2098718431","https://openalex.org/W2103608534","https://openalex.org/W2130105540","https://openalex.org/W2216785312","https://openalex.org/W3094663703"],"related_works":["https://openalex.org/W7096238567","https://openalex.org/W7095484668","https://openalex.org/W2540085067","https://openalex.org/W1949804828","https://openalex.org/W6959483656","https://openalex.org/W1983497631","https://openalex.org/W2081265789","https://openalex.org/W2544580414","https://openalex.org/W7099855024","https://openalex.org/W2727659021"],"abstract_inverted_index":{"Autonomous":[0],"helicopter":[1,25,36,60],"flight":[2],"represents":[3],"a":[4,17,30,52],"challenging":[5],"control":[6],"problem,":[7],"with":[8],"complex,":[9],"noisy,":[10],"dynamics.":[11,37],"In":[12],"this":[13],"paper,":[14],"we":[15],"describe":[16],"successful":[18],"application":[19],"of":[20,34,54],"reinforcement":[21],"learning":[22],"to":[23,43,45,50],"autonomous":[24],"flight.":[26],"We":[27,38],"first":[28],"fit":[29],"stochastic,":[31],"nonlinear":[32],"model":[33,42],"the":[35,41],"then":[39],"use":[40],"learn":[44],"hover":[46],"in":[47],"place,":[48],"and":[49],"fly":[51],"number":[53],"maneuvers":[55],"taken":[56],"from":[57],"an":[58],"RC":[59],"competition.":[61]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":16}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}