{"id":"https://openalex.org/W4387986835","doi":"https://doi.org/10.1109/tnnls.2023.3325580","title":"Differential Game-Based Deep Reinforcement Learning in Underwater Target Hunting Task","display_name":"Differential Game-Based Deep Reinforcement Learning in Underwater Target Hunting Task","publication_year":2023,"publication_date":"2023-10-27","ids":{"openalex":"https://openalex.org/W4387986835","doi":"https://doi.org/10.1109/tnnls.2023.3325580","pmid":"https://pubmed.ncbi.nlm.nih.gov/37889822"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3325580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3325580","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100323691","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0002-1748-297X"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Wei Wei","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426898","display_name":"Jingjing Wang","orcid":"https://orcid.org/0000-0003-3170-8952"},"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":"Jingjing Wang","raw_affiliation_strings":["School of Cyber Science and Technology, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033168204","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-5213-8808"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057427421","display_name":"Zhengru Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhengru Fang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002346706","display_name":"Yong Ren","orcid":"https://orcid.org/0000-0003-0312-9371"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Ren","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100643265","display_name":"C. L. Philip Chen","orcid":"https://orcid.org/0000-0001-5451-7230"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"C. L. Philip Chen","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100323691"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":7.9551,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.97856102,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"36","issue":"1","first_page":"462","last_page":"474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9921000003814697,"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":0.9921000003814697,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9904000163078308,"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/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.9718000292778015,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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":0.8078138828277588},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.7145494222640991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6925016641616821},{"id":"https://openalex.org/keywords/differential-game","display_name":"Differential game","score":0.6338076591491699},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4696713387966156},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.45747092366218567},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4209184944629669},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28277650475502014},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2199239730834961},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13017037510871887},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11406013369560242}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8078138828277588},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.7145494222640991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6925016641616821},{"id":"https://openalex.org/C2779006483","wikidata":"https://www.wikidata.org/wiki/Q1973196","display_name":"Differential game","level":2,"score":0.6338076591491699},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4696713387966156},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.45747092366218567},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4209184944629669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28277650475502014},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2199239730834961},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13017037510871887},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11406013369560242},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3325580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3325580","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37889822","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37889822","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"id":"https://metadata.un.org/sdg/14","display_name":"Life below water"}],"awards":[{"id":"https://openalex.org/G6376970105","display_name":null,"funder_award_id":"2020YFD0901000","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7799889702","display_name":null,"funder_award_id":"62071268","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7803121516","display_name":null,"funder_award_id":"L222039","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"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":28,"referenced_works":["https://openalex.org/W2173749656","https://openalex.org/W2346684976","https://openalex.org/W2408768628","https://openalex.org/W2531648764","https://openalex.org/W2568019971","https://openalex.org/W2608634483","https://openalex.org/W2734442305","https://openalex.org/W2761591697","https://openalex.org/W2898302534","https://openalex.org/W2907217398","https://openalex.org/W2954093458","https://openalex.org/W2977340802","https://openalex.org/W3008282592","https://openalex.org/W3035782080","https://openalex.org/W3086351065","https://openalex.org/W3120436174","https://openalex.org/W3152678664","https://openalex.org/W3158952689","https://openalex.org/W3167122261","https://openalex.org/W3192389740","https://openalex.org/W3214814008","https://openalex.org/W4205107701","https://openalex.org/W4221166781","https://openalex.org/W4285028943","https://openalex.org/W4286893914","https://openalex.org/W4324134829","https://openalex.org/W4391248691","https://openalex.org/W6738796088"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4283371013"],"abstract_inverted_index":{"To":[0],"meet":[1],"requirements":[2],"for":[3],"real-time":[4],"trajectory":[5],"scheduling":[6],"and":[7,22,47,67,85,104,142,177,199],"distributed":[8],"coordination,":[9],"underwater":[10,64,167],"target":[11,32,57,69,110,133,168],"hunting":[12,33,58,134,169],"task":[13,170],"is":[14,77,90,136,188],"challenging":[15],"in":[16,30,139,195],"terms":[17,196],"of":[18,61,108,174,197],"turbulent":[19],"ocean":[20],"environments":[21],"dynamic":[23,39],"adversarial":[24,81],"environment.":[25],"Despite":[26],"the":[27,86,102,106,109,116,132,140,143,151,166,172,185,191],"existing":[28],"research":[29],"game-based":[31],"area,":[34],"few":[35],"approaches":[36],"have":[37,94],"considered":[38],"environmental":[40],"factors,":[41],"such":[42],"as":[43],"sea":[44],"currents,":[45],"winds,":[46],"communication":[48],"delay.":[49,180],"In":[50,127],"this":[51],"article,":[52],"we":[53,114,156],"focus":[54],"on":[55,150],"a":[56,68,158],"system":[59,135,144],"consisted":[60],"multiple":[62],"unmanned":[63],"vehicles":[65],"(UUVs)":[66],"with":[70,119],"high":[71],"maneuverability.":[72],"Besides,":[73],"differential":[74],"game":[75],"theory":[76],"leveraged":[78],"to":[79,95,100,122,164,190],"analyze":[80],"behaviors":[82],"between":[83],"hunters":[84],"escapee.":[87],"However,":[88],"it":[89,129],"intractable":[91],"that":[92,131,184],"UUVs":[93],"deploy":[96],"an":[97],"adaptive":[98],"scheme":[99,187],"guarantee":[101],"consistency":[103],"avoid":[105],"escape":[107],"without":[111],"collision.":[112],"Therefore,":[113],"conceive":[115],"Hamiltonian":[117],"function":[118],"Leibniz's":[120],"formula":[121],"obtain":[123],"feedback":[124],"control":[125,153],"policies.":[126,154],"addition,":[128],"proves":[130],"asymptotically":[137],"stable":[138],"mean,":[141],"can":[145],"satisfy":[146],"Nash":[147],"equilibrium":[148],"relying":[149],"proposed":[152,186],"Furthermore,":[155],"design":[157],"modified":[159],"multiagent":[160],"reinforcement":[161],"learning":[162],"(MARL)":[163],"facilitate":[165],"under":[171],"constraints":[173],"energetic":[175],"flows":[176],"acoustic":[178],"propagation":[179],"Simulation":[181],"results":[182],"show":[183],"superior":[189],"typical":[192],"MARL":[193],"algorithm":[194],"reward":[198],"success":[200],"rate.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":15}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}