{"id":"https://openalex.org/W4382935954","doi":"https://doi.org/10.23919/acc55779.2023.10156379","title":"Equivariant Reinforcement Learning for Quadrotor UAV","display_name":"Equivariant Reinforcement Learning for Quadrotor UAV","publication_year":2023,"publication_date":"2023-05-31","ids":{"openalex":"https://openalex.org/W4382935954","doi":"https://doi.org/10.23919/acc55779.2023.10156379"},"language":"en","primary_location":{"id":"doi:10.23919/acc55779.2023.10156379","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc55779.2023.10156379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 American Control Conference (ACC)","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/A5028566077","display_name":"Beomyeol Yu","orcid":"https://orcid.org/0009-0007-3261-1665"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Beomyeol Yu","raw_affiliation_strings":["George Washington University,Mechanical and Aerospace Engineering,Washington, DC,20051"],"affiliations":[{"raw_affiliation_string":"George Washington University,Mechanical and Aerospace Engineering,Washington, DC,20051","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020132536","display_name":"Taeyoung Lee","orcid":"https://orcid.org/0000-0003-4982-4150"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taeyoung Lee","raw_affiliation_strings":["George Washington University,Mechanical and Aerospace Engineering,Washington, DC,20051"],"affiliations":[{"raw_affiliation_string":"George Washington University,Mechanical and Aerospace Engineering,Washington, DC,20051","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028566077"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":1.222,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82954695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2842","last_page":"2847"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9983999729156494,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9793999791145325,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9402089715003967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.676437497138977},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6001569628715515},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5707570910453796},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4818924069404602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4770761728286743},{"id":"https://openalex.org/keywords/equivariant-map","display_name":"Equivariant map","score":0.43662604689598083},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.43282246589660645},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3429543972015381},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21605271100997925},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09076458215713501}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9402089715003967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676437497138977},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6001569628715515},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5707570910453796},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4818924069404602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4770761728286743},{"id":"https://openalex.org/C171036898","wikidata":"https://www.wikidata.org/wiki/Q256355","display_name":"Equivariant map","level":2,"score":0.43662604689598083},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.43282246589660645},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3429543972015381},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21605271100997925},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09076458215713501},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc55779.2023.10156379","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc55779.2023.10156379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1564711114","https://openalex.org/W2109656638","https://openalex.org/W2113501460","https://openalex.org/W2145339207","https://openalex.org/W2163198877","https://openalex.org/W2167229184","https://openalex.org/W2558748708","https://openalex.org/W2733312032","https://openalex.org/W2741263286","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2810217655","https://openalex.org/W2907214660","https://openalex.org/W2907877674","https://openalex.org/W2985707469","https://openalex.org/W3003669699","https://openalex.org/W3020718655","https://openalex.org/W3039459278","https://openalex.org/W3127031155","https://openalex.org/W3207681582","https://openalex.org/W4200575556","https://openalex.org/W4206742276","https://openalex.org/W4286907648","https://openalex.org/W4287749615","https://openalex.org/W4295312788","https://openalex.org/W4297688279","https://openalex.org/W4298392935","https://openalex.org/W4382935954","https://openalex.org/W6694954494","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6766978945","https://openalex.org/W6767104088"],"related_works":["https://openalex.org/W3148895720","https://openalex.org/W2393913406","https://openalex.org/W30258475","https://openalex.org/W2356579025","https://openalex.org/W2736697936","https://openalex.org/W3211835374","https://openalex.org/W2548611373","https://openalex.org/W1601809778","https://openalex.org/W3169304289","https://openalex.org/W2373733345"],"abstract_inverted_index":{"This":[0,78],"paper":[1],"presents":[2],"an":[3,47],"equivariant":[4],"reinforcement":[5,16,75,86],"learning":[6,17,76,87],"framework":[7],"for":[8],"quadrotor":[9,52],"unmanned":[10],"aerial":[11],"vehicles.":[12],"Successful":[13],"training":[14,64],"of":[15,50,58,74,89],"often":[18],"requires":[19],"numerous":[20],"interactions":[21],"with":[22,84],"the":[23,31,51,56,59,63,71],"environments,":[24],"which":[25],"hinders":[26],"its":[27],"applicability":[28],"especially":[29],"when":[30,38],"available":[32],"computational":[33],"resources":[34],"are":[35],"limited,":[36],"or":[37],"there":[39],"is":[40,65,79],"no":[41],"reliable":[42],"simulation":[43],"model.":[44],"We":[45],"identified":[46],"equivariance":[48],"property":[49],"dynamics":[53],"such":[54],"that":[55],"dimension":[57],"state":[60],"required":[61],"in":[62],"reduced":[66],"by":[67,81],"one,":[68],"thereby":[69],"improving":[70],"sampling":[72],"efficiency":[73],"substantially.":[77],"illustrated":[80],"numerical":[82],"examples":[83],"popular":[85],"techniques":[88],"TD3":[90],"and":[91],"SAC.":[92]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}