{"id":"https://openalex.org/W4401168163","doi":"https://doi.org/10.1145/3674225.3674388","title":"Deep Reinforcement Learning Based Quadrotor Control with Low Function Approximation Errors","display_name":"Deep Reinforcement Learning Based Quadrotor Control with Low Function Approximation Errors","publication_year":2024,"publication_date":"2024-01-19","ids":{"openalex":"https://openalex.org/W4401168163","doi":"https://doi.org/10.1145/3674225.3674388"},"language":"en","primary_location":{"id":"doi:10.1145/3674225.3674388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674225.3674388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Power Electronics and Artificial Intelligence","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/A5100404236","display_name":"Zihao Zhang","orcid":"https://orcid.org/0000-0001-8881-6722"},"institutions":[{"id":"https://openalex.org/I4210089056","display_name":"Beijing Microelectronics Technology Institute","ror":"https://ror.org/007y7ej30","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210089056"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zihao Zhang","raw_affiliation_strings":["Beijing Microelectronics Technology Institute, China"],"raw_orcid":"https://orcid.org/0000-0001-8881-6722","affiliations":[{"raw_affiliation_string":"Beijing Microelectronics Technology Institute, China","institution_ids":["https://openalex.org/I4210089056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104338491","display_name":"Zhenlin L\u00fc","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089056","display_name":"Beijing Microelectronics Technology Institute","ror":"https://ror.org/007y7ej30","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210089056"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenlin Lu","raw_affiliation_strings":["Beijing Microelectronics Technology Institute, China"],"raw_orcid":"https://orcid.org/0009-0009-4766-3040","affiliations":[{"raw_affiliation_string":"Beijing Microelectronics Technology Institute, China","institution_ids":["https://openalex.org/I4210089056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111275272","display_name":"Yongzheng Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089056","display_name":"Beijing Microelectronics Technology Institute","ror":"https://ror.org/007y7ej30","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210089056"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongzheng Ren","raw_affiliation_strings":["Beijing Microelectronics Technology Institute, China"],"raw_orcid":"https://orcid.org/0009-0006-4794-713X","affiliations":[{"raw_affiliation_string":"Beijing Microelectronics Technology Institute, China","institution_ids":["https://openalex.org/I4210089056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002245046","display_name":"Jinye Rong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089056","display_name":"Beijing Microelectronics Technology Institute","ror":"https://ror.org/007y7ej30","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210089056"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinye Rong","raw_affiliation_strings":["Beijing Microelectronics Technology Institute, China"],"raw_orcid":"https://orcid.org/0009-0005-0831-9723","affiliations":[{"raw_affiliation_string":"Beijing Microelectronics Technology Institute, China","institution_ids":["https://openalex.org/I4210089056"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuai Wang","orcid":"https://orcid.org/0009-0004-8732-7977"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["School of Software, Beihang University, China"],"raw_orcid":"https://orcid.org/0009-0004-8732-7977","affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022393617","display_name":"Shikai Sun","orcid":"https://orcid.org/0009-0002-7479-5910"},"institutions":[{"id":"https://openalex.org/I4210089056","display_name":"Beijing Microelectronics Technology Institute","ror":"https://ror.org/007y7ej30","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210089056"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikai Sun","raw_affiliation_strings":["Beijing Microelectronics Technology Institute, China"],"raw_orcid":"https://orcid.org/0009-0002-7479-5910","affiliations":[{"raw_affiliation_string":"Beijing Microelectronics Technology Institute, China","institution_ids":["https://openalex.org/I4210089056"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100404236"],"corresponding_institution_ids":["https://openalex.org/I4210089056"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1424266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"907","last_page":"911"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9979000091552734,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.8219846487045288},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6187905073165894},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.5365490913391113},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49465104937553406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4583745002746582},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43439921736717224},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.39607298374176025},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16049152612686157}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8219846487045288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6187905073165894},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5365490913391113},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49465104937553406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4583745002746582},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43439921736717224},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.39607298374176025},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16049152612686157},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3674225.3674388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674225.3674388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Power Electronics and Artificial Intelligence","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":14,"referenced_works":["https://openalex.org/W2155968351","https://openalex.org/W2173248099","https://openalex.org/W2736601468","https://openalex.org/W2787938642","https://openalex.org/W3005243570","https://openalex.org/W3009674568","https://openalex.org/W3037989090","https://openalex.org/W3041202696","https://openalex.org/W3126413449","https://openalex.org/W3142824457","https://openalex.org/W3153187775","https://openalex.org/W4200438872","https://openalex.org/W4364322852","https://openalex.org/W4386590944"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3021988786","https://openalex.org/W3099311996","https://openalex.org/W2963971282"],"abstract_inverted_index":{"With":[0],"the":[1,14,30,46,52,74,90,94,104,125,129,134,140,145,151],"rapid":[2],"popularization":[3],"and":[4,16,63,123,154,160,191],"application":[5],"of":[6,18,25,34,48,54,96,128,139],"UAVs,":[7],"higher":[8,179],"requirements":[9],"are":[10],"put":[11],"forward":[12],"for":[13],"performance":[15,40],"efficiency":[17],"UAV":[19,42],"control":[20],"methods.":[21],"A":[22],"large":[23],"number":[24],"scholars":[26],"have":[27,68],"verified":[28],"that":[29,175],"machine":[31],"learning":[32,37,78,116],"method":[33,79],"deep":[35],"reinforcement":[36,77],"has":[38,178],"good":[39],"on":[41,100,114],"control.":[43,84],"However,":[44],"in":[45,73,82,162],"process":[47,142],"value":[49,127],"function":[50,55,97],"iteration,":[51],"error":[53],"estimation":[56,98],"is":[57],"inevitable,":[58],"which":[59],"leads":[60],"to":[61,71,92,143],"overestimation":[62],"sub-optimal":[64],"strategy.":[65],"Related":[66],"problems":[67],"been":[69],"proven":[70],"exist":[72],"actor-critic":[75,105],"framework":[76],"commonly":[80],"used":[81],"quadrotor":[83],"In":[85],"this":[86],"paper,":[87],"we":[88,107],"modified":[89],"algorithm":[91,101,153,177],"reduce":[93],"impact":[95],"errors":[99],"performance.":[102],"Under":[103],"framework,":[106],"build":[108],"our":[109,176],"algorithm's":[110],"critic":[111,121],"network":[112,122],"based":[113],"Q":[115],"method,":[117],"with":[118,187],"a":[119,163,188],"double":[120],"take":[124],"smaller":[126],"these":[130],"two":[131,155],"outputs":[132],"as":[133],"temporal":[135],"difference":[136],"(TD)":[137],"target":[138],"training":[141],"limit":[144],"overestimation.":[146],"We":[147],"conducted":[148],"simulations":[149],"using":[150],"developed":[152],"other":[156],"popular":[157],"algorithms":[158],"PPO":[159],"DDPG":[161],"pybullet":[164],"made":[165],"environment":[166],"modeled":[167],"by":[168],"real":[169],"quadrotor.":[170],"The":[171],"experimental":[172],"results":[173],"show":[174],"average":[180],"rewards":[181],"under":[182],"three":[183],"different":[184],"task":[185],"settings":[186],"general":[189],"29.04%":[190],"14.59%":[192],"improvement.":[193]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}