{"id":"https://openalex.org/W2062122188","doi":"https://doi.org/10.1145/1015330.1015384","title":"Learning to fly by combining reinforcement learning with behavioural cloning","display_name":"Learning to fly by combining reinforcement learning with behavioural cloning","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2062122188","doi":"https://doi.org/10.1145/1015330.1015384","mag":"2062122188"},"language":"en","primary_location":{"id":"doi:10.1145/1015330.1015384","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1015330.1015384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twenty-first international conference on Machine learning  - ICML '04","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/A5035687300","display_name":"Eduardo F. Morales","orcid":"https://orcid.org/0000-0002-7618-8762"},"institutions":[{"id":"https://openalex.org/I98461037","display_name":"Tecnol\u00f3gico de Monterrey","ror":"https://ror.org/03ayjn504","country_code":"MX","type":"education","lineage":["https://openalex.org/I98461037"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Eduardo F. Morales","raw_affiliation_strings":["Tec de Monterrey - Campus Cuernavaca, Temixco, Morelos, M\u00e9xico#TAB#"],"affiliations":[{"raw_affiliation_string":"Tec de Monterrey - Campus Cuernavaca, Temixco, Morelos, M\u00e9xico#TAB#","institution_ids":["https://openalex.org/I98461037"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015779172","display_name":"Claude Sammut","orcid":"https://orcid.org/0000-0001-8873-5228"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Claude Sammut","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035687300"],"corresponding_institution_ids":["https://openalex.org/I98461037"],"apc_list":null,"apc_paid":null,"fwci":3.697,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.93150074,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9890000224113464,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9890000224113464,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9860000014305115,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8391728401184082},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.6480840444564819},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6268672943115234},{"id":"https://openalex.org/keywords/on-the-fly","display_name":"On the fly","score":0.6221233010292053},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.527253270149231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4539787471294403},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35699158906936646},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33597564697265625},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1698532998561859},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09947898983955383},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05516412854194641}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8391728401184082},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.6480840444564819},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6268672943115234},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.6221233010292053},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.527253270149231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4539787471294403},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35699158906936646},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33597564697265625},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1698532998561859},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09947898983955383},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05516412854194641},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1015330.1015384","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1015330.1015384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twenty-first international conference on Machine learning  - ICML '04","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.5689","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.5689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aicml.cs.ualberta.ca/banff04/icml/pages/papers/187.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.578.4422","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.578.4422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ccc.inaoep.mx/~emorales/Papers/2004/icml04fin2.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.6686","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.6686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://kingman.cs.ualberta.ca/_banff04/icml/pages/papers/187.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320965","display_name":"University of New South Wales","ror":"https://ror.org/03r8z3t63"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W198956113","https://openalex.org/W1511887321","https://openalex.org/W1585546346","https://openalex.org/W1853714515","https://openalex.org/W1855398616","https://openalex.org/W2108734173","https://openalex.org/W2125510930","https://openalex.org/W2170396035","https://openalex.org/W3020831056","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2107890255","https://openalex.org/W2089013912","https://openalex.org/W2106552856","https://openalex.org/W2076061571","https://openalex.org/W2038908348","https://openalex.org/W2072376847","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,4,28,98,122],"deals":[2],"with":[3,12,17,25,81],"optimal":[5,8,104],"or":[6],"near":[7],"policies":[9,59],"while":[10],"inter-acting":[11],"the":[13,32,93],"environment.":[14],"Application":[15],"domains":[16],"many":[18],"continuous":[19],"variables":[20],"are":[21],"dicult":[22],"to":[23,31,44,51,68,101,130,133],"solve":[24],"existing":[26],"reinforcement":[27,97],"methods":[29],"due":[30],"large":[33],"search":[34],"space.":[35,109],"In":[36],"this":[37,107],"paper,":[38],"we":[39],"use":[40],"a":[41,76,115,124],"relational":[42,125],"rep-resentation":[43],"dene":[45],"powerful":[46,128],"abstractions":[47],"that":[48],"allow":[49],"us":[50],"incorporate":[52],"domain":[53],"knowl-edge":[54],"and":[55,120,142],"re-use":[56],"previously":[57],"learned":[58],"in":[60,140],"other":[61],"similar":[62],"problems.":[63],"We":[64],"also":[65],"describe":[66],"how":[67,114,132],"learn":[69,102,131],"useful":[70],"actions":[71,88],"from":[72],"human":[73],"traces":[74],"us-ing":[75],"behavioural":[77,118],"cloning":[78,119],"approach":[79],"combined":[80],"an":[82,103,135],"exploration":[83],"phase.":[84],"Since":[85],"several":[86],"con-icting":[87],"may":[89],"be":[90],"induced":[91],"for":[92],"same":[94],"abstract":[95],"state,":[96],"is":[99,111,127],"used":[100],"policy":[105],"over":[106],"reduced":[108],"It":[110],"shown":[112],"experimentally":[113],"com-bination":[116],"of":[117],"reinforce-ment":[121],"using":[123],"representa-tion":[126],"enough":[129],"\\ny":[134],"aircraft":[136],"through":[137],"dierent":[138,143],"points":[139],"space":[141],"turbulence":[144],"conditions.":[145],"1.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
