{"id":"https://openalex.org/W4415969686","doi":"https://doi.org/10.1109/iecon58223.2025.11221157","title":"A Hierarchical Reinforcement Learning Method in Multi-UAV Target-Attacker-Defender Games","display_name":"A Hierarchical Reinforcement Learning Method in Multi-UAV Target-Attacker-Defender Games","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W4415969686","doi":"https://doi.org/10.1109/iecon58223.2025.11221157"},"language":null,"primary_location":{"id":"doi:10.1109/iecon58223.2025.11221157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon58223.2025.11221157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2025 \u2013 51st Annual Conference of the IEEE Industrial Electronics Society","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/A5003328070","display_name":"Xilun Li","orcid":"https://orcid.org/0000-0002-5794-0074"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilun Li","raw_affiliation_strings":["Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xubin Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xubin Zhou","raw_affiliation_strings":["Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057565126","display_name":"Yipeng Yang","orcid":"https://orcid.org/0000-0002-0315-0886"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yipeng Yang","raw_affiliation_strings":["Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015335824","display_name":"Xuebo Yang","orcid":"https://orcid.org/0000-0001-8609-085X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuebo Yang","raw_affiliation_strings":["Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101675568","display_name":"Zhan Li","orcid":"https://orcid.org/0009-0003-3935-9694"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Li","raw_affiliation_strings":["Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39696957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.5490000247955322,"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":0.5490000247955322,"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":0.2167000025510788,"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/T13371","display_name":"Military Defense Systems Analysis","score":0.05310000106692314,"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":0.8540999889373779},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6559000015258789},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5965999960899353},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.574999988079071},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.5189999938011169},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.3955000042915344},{"id":"https://openalex.org/keywords/differential-game","display_name":"Differential game","score":0.36059999465942383}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8540999889373779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7135000228881836},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6559000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6227999925613403},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5965999960899353},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.574999988079071},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4172999858856201},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C2779006483","wikidata":"https://www.wikidata.org/wiki/Q1973196","display_name":"Differential game","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.34150001406669617},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2806999981403351},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iecon58223.2025.11221157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon58223.2025.11221157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2025 \u2013 51st Annual Conference of the IEEE Industrial Electronics Society","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2076554191","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2800797998","https://openalex.org/W2962769637","https://openalex.org/W3123009522","https://openalex.org/W3166816823","https://openalex.org/W3214814008","https://openalex.org/W4212996499","https://openalex.org/W4313459893","https://openalex.org/W4321608043","https://openalex.org/W4388720294","https://openalex.org/W4388740240","https://openalex.org/W4408282148"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"analyze":[4],"a":[5,20,50,60,100],"multi-UAV":[6],"target-attacker-defender":[7],"(TAD)":[8],"differential":[9,82],"game":[10,83],"framework":[11,48],"in":[12],"which":[13],"multiple":[14],"defenders":[15,38,69],"is":[16],"tasked":[17],"with":[18,73],"shielding":[19],"target":[21,74],"from":[22],"several":[23],"attackers.":[24],"The":[25,96],"attackers":[26,75],"are":[27,70,89],"driven":[28],"by":[29,81],"the":[30,34,37,54,66,93,118],"objective":[31],"of":[32],"seizing":[33],"target,":[35],"while":[36],"focus":[39],"on":[40],"intercepting":[41],"their":[42],"advances.":[43],"Hierarchical":[44],"reinforcement":[45],"learning":[46],"(HRL)":[47],"offers":[49],"promising":[51],"strategy":[52],"for":[53,112],"TAD":[55],"problem.":[56],"This":[57],"work":[58],"introduces":[59],"two-level":[61],"goal-conditioned":[62],"HRL":[63],"method.":[64,124],"At":[65],"first":[67],"level,":[68],"dynamically":[71],"paired":[72],"through":[76],"an":[77],"assignment":[78],"mechanism":[79],"guided":[80],"theory,":[84],"where":[85],"optimal":[86],"intercept":[87],"trajectories":[88],"computed":[90],"to":[91,108,122],"inform":[92],"matching":[94],"process.":[95],"second":[97],"level":[98],"employs":[99],"multi-agent":[101],"deep":[102],"deterministic":[103],"policy":[104],"gradient":[105],"(MADDPG)":[106],"algorithm":[107],"derive":[109],"coordinated":[110],"policies":[111],"both":[113],"teams.":[114],"Experimental":[115],"validation":[116],"demonstrates":[117],"framework\u2019s":[119],"effectiveness":[120],"compared":[121],"baseline":[123]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-06T00:00:00"}