{"id":"https://openalex.org/W4375929017","doi":"https://doi.org/10.1109/tsmc.2023.3270444","title":"A Hierarchical Deep Reinforcement Learning Framework for 6-DOF UCAV Air-to-Air Combat","display_name":"A Hierarchical Deep Reinforcement Learning Framework for 6-DOF UCAV Air-to-Air Combat","publication_year":2023,"publication_date":"2023-05-08","ids":{"openalex":"https://openalex.org/W4375929017","doi":"https://doi.org/10.1109/tsmc.2023.3270444"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2023.3270444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2023.3270444","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-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/A5073383645","display_name":"Jiajun Chai","orcid":"https://orcid.org/0000-0002-7611-064X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Chai","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7611-064X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949856","display_name":"Wenzhang Chen","orcid":"https://orcid.org/0009-0003-3395-0221"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhang Chen","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-3395-0221","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5384-423X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064816809","display_name":"Zongxin Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I125904092","display_name":"Shenyang Aerospace University","ror":"https://ror.org/02423gm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I125904092"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zong-Xin Yao","raw_affiliation_strings":["Department of Unmanned Aerial Vehicle, Shenyang Aircraft Design and Research Institute, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Unmanned Aerial Vehicle, Shenyang Aircraft Design and Research Institute, Shenyang, China","institution_ids":["https://openalex.org/I125904092"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8218-9633","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":52.566,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.9988389,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"53","issue":"9","first_page":"5417","last_page":"5429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.9972000122070312,"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"}},"topics":[{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.9972000122070312,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9865000247955322,"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":0.9311000108718872,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8486624360084534},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.796129047870636},{"id":"https://openalex.org/keywords/air-combat","display_name":"Air combat","score":0.779900312423706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5667293667793274},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5617516040802002},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.5019035339355469},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4756039083003998},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44255462288856506},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3793303370475769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3454868793487549},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.26928621530532837}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8486624360084534},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.796129047870636},{"id":"https://openalex.org/C2988296547","wikidata":"https://www.wikidata.org/wiki/Q471145","display_name":"Air combat","level":2,"score":0.779900312423706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5667293667793274},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5617516040802002},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.5019035339355469},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4756039083003998},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44255462288856506},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3793303370475769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3454868793487549},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.26928621530532837},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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:10.1109/tsmc.2023.3270444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2023.3270444","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G2968709009","display_name":null,"funder_award_id":"2018AAA0101005","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6023506935","display_name":null,"funder_award_id":"XDA27030400","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G8179479325","display_name":null,"funder_award_id":"62293541","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1762421970","https://openalex.org/W1906530935","https://openalex.org/W2075110355","https://openalex.org/W2079682569","https://openalex.org/W2094990636","https://openalex.org/W2119895056","https://openalex.org/W2121391769","https://openalex.org/W2125076089","https://openalex.org/W2145339207","https://openalex.org/W2515894276","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2769037371","https://openalex.org/W2791797404","https://openalex.org/W2884150506","https://openalex.org/W2898904083","https://openalex.org/W2903604929","https://openalex.org/W2907275873","https://openalex.org/W2913448405","https://openalex.org/W2953029955","https://openalex.org/W2963890729","https://openalex.org/W2982316857","https://openalex.org/W2989295242","https://openalex.org/W2996726407","https://openalex.org/W2998655286","https://openalex.org/W3005593860","https://openalex.org/W3018030060","https://openalex.org/W3039802322","https://openalex.org/W3084241738","https://openalex.org/W3107097976","https://openalex.org/W3110979110","https://openalex.org/W3158636884","https://openalex.org/W3190154035","https://openalex.org/W3196869853","https://openalex.org/W3196924932","https://openalex.org/W3199414640","https://openalex.org/W3202614762","https://openalex.org/W3207544809","https://openalex.org/W3217091241","https://openalex.org/W4210366873","https://openalex.org/W4214820954","https://openalex.org/W4296426247","https://openalex.org/W6627932998","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6752963931","https://openalex.org/W6771787661","https://openalex.org/W6782204448"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4404955202"],"abstract_inverted_index":{"Unmanned":[0],"combat":[1,5,36,72,83,148,159,166,190],"air":[2],"vehicle":[3],"(UCAV)":[4],"is":[6,48],"a":[7,26,71,90,126,152],"challenging":[8],"scenario":[9],"with":[10],"high-dimensional":[11],"continuous":[12],"state":[13],"and":[14,17,58,117],"action":[15],"space":[16],"highly":[18],"nonlinear":[19],"dynamics.":[20,44],"In":[21],"this":[22],"article,":[23],"we":[24,134,150],"propose":[25],"general":[27],"hierarchical":[28],"framework":[29],"to":[30,49,63,74,80,93,140,156],"resolve":[31],"the":[32,51,76,81,86,95,100,105,109,114,118,131,147,158,164,172],"within-vision-range":[33],"(WVR)":[34],"air-to-air":[35],"problem":[37],"under":[38],"six":[39],"dimensions":[40],"of":[41],"degree":[42],"(6-DOF)":[43],"The":[45,67,183],"core":[46],"idea":[47],"divide":[50],"whole":[52],"decision-making":[53,111],"process":[54,112],"into":[55],"two":[56,122],"loops":[57],"use":[59],"reinforcement":[60],"learning":[61],"(RL)":[62],"solve":[64],"them":[65],"separately.":[66],"outer":[68],"loop":[69,88],"uses":[70,89],"policy":[73,92,116,174],"decide":[75],"macro":[77,96,144],"command":[78,97],"according":[79],"current":[82],"situation.":[84],"Then":[85],"inner":[87],"control":[91,115,132,173],"answer":[94],"by":[98,161],"calculating":[99],"actual":[101],"input":[102],"signals":[103],"for":[104,113],"aircraft.":[106,123],"We":[107,124],"design":[108,135],"Markov":[110,119],"game":[120],"between":[121],"present":[125,151],"two-stage":[127],"training":[128],"mechanism.":[129],"For":[130,146],"policy,":[133,149,191],"an":[136],"effective":[137],"reward":[138],"function":[139],"accurately":[141],"track":[142],"various":[143],"behaviors.":[145],"fictitious":[153,184],"self-play":[154,185],"mechanism":[155,186],"improve":[157],"performance":[160,179],"combating":[162],"against":[163,198],"historical":[165],"policies.":[167],"Experiment":[168],"results":[169],"show":[170],"that":[171],"can":[175,187,193],"achieve":[176,194],"better":[177],"tracking":[178],"than":[180],"conventional":[181,199],"methods.":[182,200],"learn":[188],"competitive":[189],"which":[192],"high":[195],"winning":[196],"rates":[197]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}