{"id":"https://openalex.org/W4409473658","doi":"https://doi.org/10.1109/tase.2025.3560757","title":"Observer-Based Multi-Agent Reinforcement Learning for Pursuit-Evasion Game With Multiple Unknown Uncertainties","display_name":"Observer-Based Multi-Agent Reinforcement Learning for Pursuit-Evasion Game With Multiple Unknown Uncertainties","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409473658","doi":"https://doi.org/10.1109/tase.2025.3560757"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2025.3560757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3560757","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","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/A5100393327","display_name":"Yangyang Liu","orcid":"https://orcid.org/0009-0006-4563-0155"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangyang Liu","raw_affiliation_strings":["School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-4563-0155","affiliations":[{"raw_affiliation_string":"School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005307243","display_name":"Chun Liu","orcid":"https://orcid.org/0000-0002-9294-6519"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Liu","raw_affiliation_strings":["School of Mechatronic Engineering and Automation and the Institute of Artificial Intelligence, Shanghai University, Shanghai, China","School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9294-6519","affiliations":[{"raw_affiliation_string":"School of Mechatronic Engineering and Automation and the Institute of Artificial Intelligence, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]},{"raw_affiliation_string":"School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101434993","display_name":"Yizhen Meng","orcid":"https://orcid.org/0000-0001-6466-3565"},"institutions":[{"id":"https://openalex.org/I2802615301","display_name":"China Aerospace Science and Technology Corporation","ror":"https://ror.org/01z8tr155","country_code":"CN","type":"government","lineage":["https://openalex.org/I2802615301"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhen Meng","raw_affiliation_strings":["National Key Laboratory of Space Target Awareness, Shanghai Aerospace Control Technology Institute, Shanghai, China","Shanghai Aerospace Control Technology Institute, Shanghai Key Laboratory of Aerospace Intelligent Control Technology, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6466-3565","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Space Target Awareness, Shanghai Aerospace Control Technology Institute, Shanghai, China","institution_ids":["https://openalex.org/I2802615301"]},{"raw_affiliation_string":"Shanghai Aerospace Control Technology Institute, Shanghai Key Laboratory of Aerospace Intelligent Control Technology, Shanghai, China","institution_ids":["https://openalex.org/I2802615301"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019157263","display_name":"Bin Jiang","orcid":"https://orcid.org/0000-0003-2696-5436"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Jiang","raw_affiliation_strings":["College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-2696-5436","affiliations":[{"raw_affiliation_string":"College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100718391","display_name":"Xiaofan Wang","orcid":"https://orcid.org/0000-0003-0295-2462"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I67001856","display_name":"Shanghai Institute of Technology","ror":"https://ror.org/00fjzqj15","country_code":"CN","type":"education","lineage":["https://openalex.org/I67001856"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofan Wang","raw_affiliation_strings":["Shanghai Institute of Technology, Shanghai, China","School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0295-2462","affiliations":[{"raw_affiliation_string":"Shanghai Institute of Technology, Shanghai, China","institution_ids":["https://openalex.org/I67001856"]},{"raw_affiliation_string":"School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.9582,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98718037,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"22","issue":null,"first_page":"14332","last_page":"14345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.9939000010490417,"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":0.9939000010490417,"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/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9035999774932861,"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":0.6281149387359619},{"id":"https://openalex.org/keywords/pursuit-evasion","display_name":"Pursuit-evasion","score":0.6076540350914001},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.5969371199607849},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5803996324539185},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5377523899078369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4382408857345581},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.32781434059143066},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3260727524757385},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.30171817541122437}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6281149387359619},{"id":"https://openalex.org/C2778388243","wikidata":"https://www.wikidata.org/wiki/Q7261573","display_name":"Pursuit-evasion","level":2,"score":0.6076540350914001},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.5969371199607849},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5803996324539185},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5377523899078369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4382408857345581},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.32781434059143066},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3260727524757385},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.30171817541122437},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2025.3560757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3560757","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4405644799","display_name":null,"funder_award_id":"62336005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5336079314","display_name":null,"funder_award_id":"22JC1401401","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G5779413134","display_name":null,"funder_award_id":"62333011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6327818892","display_name":null,"funder_award_id":"62273223","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/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2058111864","https://openalex.org/W2132244213","https://openalex.org/W2484646121","https://openalex.org/W2528521450","https://openalex.org/W2888559564","https://openalex.org/W2920945592","https://openalex.org/W3005440972","https://openalex.org/W3093345403","https://openalex.org/W3153781554","https://openalex.org/W3185539947","https://openalex.org/W3200722893","https://openalex.org/W3205953818","https://openalex.org/W4213053159","https://openalex.org/W4213246061","https://openalex.org/W4225659902","https://openalex.org/W4226053079","https://openalex.org/W4228997899","https://openalex.org/W4285169373","https://openalex.org/W4293863350","https://openalex.org/W4297032903","https://openalex.org/W4309367642","https://openalex.org/W4312548927","https://openalex.org/W4312987110","https://openalex.org/W4382658113","https://openalex.org/W4385444705","https://openalex.org/W4387245268","https://openalex.org/W4388692666","https://openalex.org/W4388740240","https://openalex.org/W4389879635","https://openalex.org/W4390480853","https://openalex.org/W4390492561","https://openalex.org/W4391791320","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6802002411"],"related_works":["https://openalex.org/W2057376130","https://openalex.org/W2091926052","https://openalex.org/W3150610856","https://openalex.org/W3205502940","https://openalex.org/W2968032608","https://openalex.org/W4287241423","https://openalex.org/W63592443","https://openalex.org/W4400884118","https://openalex.org/W2167407230","https://openalex.org/W2019877704"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"to":[3,39,54,88,137,142],"investigate":[4],"the":[5,56,67,78,82,89,93,117,124,145,172,176,179,184],"challenging":[6],"problem":[7],"of":[8,58,81,126,147,178],"a":[9,16,107,152],"multi-agent":[10],"game":[11,154],"with":[12,22,41,61,97],"multiple":[13,23],"pursuers":[14],"and":[15,32,133,150,168],"single":[17],"evader":[18],"in":[19,105,123,130,183],"an":[20],"environment":[21],"unknown":[24],"uncertainties.":[25],"A":[26],"coupled":[27],"approach":[28],"combining":[29],"decentralized":[30,45],"observers":[31,46,149],"reinforcement":[33],"learning":[34],"(RL)":[35],"controllers":[36,94],"is":[37,112,155],"proposed":[38],"deal":[40],"this":[42],"scenario.":[43],"Firstly,":[44],"driven":[47],"by":[48,164],"auxiliary":[49],"control":[50,167],"laws":[51],"are":[52,85,95,162],"introduced":[53],"estimate":[55],"states":[57,80],"uncertain":[59],"systems,":[60,84],"their":[62],"best":[63],"responses":[64],"obtained":[65],"through":[66],"adaptive":[68],"dynamic":[69],"programming":[70],"(ADP)":[71],"method.":[72],"The":[73,114],"estimated":[74],"states,":[75],"which":[76,106],"reflect":[77],"actual":[79],"pursuers\u2019":[83],"concurrently":[86],"transmitted":[87],"RL":[90],"controllers.":[91],"Subsequently,":[92],"trained":[96],"observer-based":[98],"heterogeneous-agent":[99],"proximal":[100],"policy":[101,121],"optimization":[102],"(OHAPPO)":[103],"algorithm,":[104],"novel":[108],"global":[109],"multi-function":[110],"cost":[111],"designed.":[113],"algorithm":[115,182],"utilizes":[116],"advantage":[118],"decomposition":[119],"for":[120],"updates":[122,135],"way":[125],"credit":[127],"assignment,":[128],"resulting":[129],"more":[131],"stable":[132],"efficient":[134],"compared":[136],"traditional":[138],"value":[139],"decomposition.":[140],"Moreover,":[141],"further":[143],"enhance":[144],"performance":[146],"both":[148],"controllers,":[151],"sequential":[153],"established":[156],"between":[157],"them,":[158],"where":[159],"observers\u2019":[160],"policies":[161],"influenced":[163],"controllers\u2019":[165],"optimal":[166],"vice":[169],"versa.":[170],"Finally,":[171],"simulation":[173],"results":[174],"verify":[175],"effectiveness":[177],"designed":[180],"OHAPPO":[181],"pursuit-evasion":[185],"game.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}