{"id":"https://openalex.org/W4406793899","doi":"https://doi.org/10.1109/tits.2024.3524562","title":"Extrinsic-and-Intrinsic Reward-Based Multi-Agent Reinforcement Learning for Multi-UAV Cooperative Target Encirclement","display_name":"Extrinsic-and-Intrinsic Reward-Based Multi-Agent Reinforcement Learning for Multi-UAV Cooperative Target Encirclement","publication_year":2025,"publication_date":"2025-01-24","ids":{"openalex":"https://openalex.org/W4406793899","doi":"https://doi.org/10.1109/tits.2024.3524562"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2024.3524562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2024.3524562","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation 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/A5086071901","display_name":"Jinchao Chen","orcid":"https://orcid.org/0000-0001-6234-1001"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinchao Chen","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108998951","display_name":"Yang Wang","orcid":"https://orcid.org/0009-0009-9056-3344"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386171","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0002-7557-2965"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077680871","display_name":"Yantao Lu","orcid":"https://orcid.org/0000-0002-3103-1067"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yantao Lu","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050629111","display_name":"Qiuhao Shu","orcid":"https://orcid.org/0009-0001-4714-5915"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuhao Shu","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030898736","display_name":"Yujiao Hu","orcid":"https://orcid.org/0000-0002-2271-1810"},"institutions":[{"id":"https://openalex.org/I4210155350","display_name":"Purple Mountain Laboratories","ror":"https://ror.org/04zcbk583","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210155350"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujiao Hu","raw_affiliation_strings":["Future Network Research Center, Purple Mountain Laboratories, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Future Network Research Center, Purple Mountain Laboratories, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I4210155350"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5086071901"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":44.7268,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.99857195,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"26","issue":"10","first_page":"17653","last_page":"17665"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.876800000667572,"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"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.876800000667572,"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"}},{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.7750999927520752,"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/T13371","display_name":"Military Defense Systems Analysis","score":0.7648000121116638,"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":0.8503607511520386},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.584943950176239},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5124971866607666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3441568911075592},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.27789822220802307},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.08650991320610046}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8503607511520386},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.584943950176239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5124971866607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3441568911075592},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27789822220802307},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.08650991320610046}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2024.3524562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2024.3524562","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1396483212","display_name":null,"funder_award_id":"2023M073053003","funder_id":"https://openalex.org/F4320322857","funder_display_name":"Aeronautical Science Foundation of China"},{"id":"https://openalex.org/G8178281889","display_name":null,"funder_award_id":"62106202","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/F4320322857","display_name":"Aeronautical Science Foundation of China","ror":"https://ror.org/02wq41p38"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2012518714","https://openalex.org/W2592570835","https://openalex.org/W2903253065","https://openalex.org/W2978145949","https://openalex.org/W2981288310","https://openalex.org/W2998280308","https://openalex.org/W2998566163","https://openalex.org/W2999032021","https://openalex.org/W3015082424","https://openalex.org/W3104686123","https://openalex.org/W3105649577","https://openalex.org/W3127561923","https://openalex.org/W3142077573","https://openalex.org/W3151306683","https://openalex.org/W3154290186","https://openalex.org/W3196698656","https://openalex.org/W3210448484","https://openalex.org/W3216423264","https://openalex.org/W4206270770","https://openalex.org/W4213246061","https://openalex.org/W4285028943","https://openalex.org/W4286361939","https://openalex.org/W4290792262","https://openalex.org/W4308981848","https://openalex.org/W4312334862","https://openalex.org/W4312830493","https://openalex.org/W4313269729","https://openalex.org/W4317437777","https://openalex.org/W4376639611","https://openalex.org/W4380989564","https://openalex.org/W4383500888","https://openalex.org/W4387952116","https://openalex.org/W4388505508","https://openalex.org/W4389478889"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Due":[0],"to":[1,42,69,76,130,146,167],"their":[2],"high":[3],"flexibility":[4],"and":[5,17,36,38,43,50,67,87,96,102,133,153,174,195],"strong":[6],"maneuverability,":[7],"unmanned":[8],"aerial":[9],"vehicles":[10],"(UAVs)":[11],"have":[12,30],"attracted":[13],"lots":[14],"of":[15,64,84,100,151,171,187],"attention":[16],"are":[18,165],"widely":[19],"employed":[20],"in":[21,25,34,48,185],"many":[22],"fields.":[23],"Especially":[24],"target":[26,61,106,156],"encirclement":[27,62,107,157,190,193,196],"applications,":[28],"UAVs":[29,66,86,152],"shown":[31],"great":[32],"advantages":[33],"adaptability":[35],"reliability,":[37],"can":[39],"efficiently":[40],"fly":[41],"evenly":[44],"surround":[45],"the":[46,59,78,82,91,104,118,149,155,169,175],"targets":[47],"complex":[49],"dynamic":[51],"environments.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,89,137],"concentrate":[57],"on":[58],"cooperative":[60,105],"problem":[63,108],"heterogeneous":[65,85],"try":[68],"propose":[70,138],"a":[71,110,125,182],"multi-agent":[72,142],"reinforcement":[73,143],"learning":[74,120,144],"approach":[75,145,180],"solve":[77],"problem.":[79],"First,":[80],"with":[81,161],"models":[83],"obstacles,":[88],"analyze":[90],"collision":[92],"avoidance,":[93],"motion":[94],"continuity,":[95],"energy":[97,197],"consumption":[98],"constraints":[99],"UAVs,":[101],"formulate":[103],"as":[109],"multi-constraint":[111],"combinatorial":[112],"optimization":[113],"one.":[114],"Then,":[115],"inspired":[116],"by":[117],"humans\u2019":[119],"experience":[121],"that":[122,178],"curiosity":[123],"provides":[124],"powerful":[126],"motivator":[127],"for":[128],"humans":[129],"explore,":[131],"discover,":[132],"acquire":[134],"new":[135],"knowledge,":[136],"an":[139],"extrinsic-and-intrinsic":[140],"reward-based":[141],"cooperatively":[147],"control":[148],"behaviors":[150],"achieve":[154],"missions.":[158],"Simulation":[159],"experiments":[160],"randomly":[162],"generated":[163],"environments":[164],"conducted":[166],"evaluate":[168],"performance":[170],"our":[172,179],"approach,":[173],"results":[176],"show":[177],"has":[181],"significant":[183],"advantage":[184],"terms":[186],"average":[188],"reward,":[189],"success":[191],"rate,":[192],"time,":[194],"consumption.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":27}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}