{"id":"https://openalex.org/W4402260360","doi":"https://doi.org/10.23919/acc60939.2024.10644476","title":"Optimal Capture Strategy Design Based on Reinforcement Learning in the Pursuit-Evasion Game with Unknown Dynamics","display_name":"Optimal Capture Strategy Design Based on Reinforcement Learning in the Pursuit-Evasion Game with Unknown Dynamics","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4402260360","doi":"https://doi.org/10.23919/acc60939.2024.10644476"},"language":"en","primary_location":{"id":"doi:10.23919/acc60939.2024.10644476","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc60939.2024.10644476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","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/A5103014665","display_name":"Yupeng Jia","orcid":"https://orcid.org/0009-0001-2654-5629"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yupeng Jia","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University,Shanghai,P. R. China,200092"],"affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University,Shanghai,P. R. China,200092","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047342501","display_name":"Yi Dong","orcid":"https://orcid.org/0000-0002-1687-535X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Dong","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University,Shanghai,P. R. China,200092"],"affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University,Shanghai,P. R. China,200092","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103014665"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.3804,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63866162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2685","last_page":"2690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9988999962806702,"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/T12158","display_name":"Guidance and Control Systems","score":0.9961000084877014,"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":0.9904000163078308,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pursuit-evasion","display_name":"Pursuit-evasion","score":0.8318098783493042},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7917314171791077},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6772760152816772},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.55728679895401},{"id":"https://openalex.org/keywords/evasion","display_name":"Evasion (ethics)","score":0.5174777507781982},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4537723958492279},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.4295838475227356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3588751554489136},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.18878096342086792},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1538316309452057},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06854307651519775}],"concepts":[{"id":"https://openalex.org/C2778388243","wikidata":"https://www.wikidata.org/wiki/Q7261573","display_name":"Pursuit-evasion","level":2,"score":0.8318098783493042},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7917314171791077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6772760152816772},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.55728679895401},{"id":"https://openalex.org/C2781251061","wikidata":"https://www.wikidata.org/wiki/Q5416089","display_name":"Evasion (ethics)","level":3,"score":0.5174777507781982},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4537723958492279},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.4295838475227356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3588751554489136},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.18878096342086792},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1538316309452057},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06854307651519775},{"id":"https://openalex.org/C203014093","wikidata":"https://www.wikidata.org/wiki/Q101929","display_name":"Immunology","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C8891405","wikidata":"https://www.wikidata.org/wiki/Q1059","display_name":"Immune system","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc60939.2024.10644476","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc60939.2024.10644476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G5371711230","display_name":null,"funder_award_id":"22QA1409400","funder_id":"https://openalex.org/F4320327803","funder_display_name":"Shanghai Rising-Star Program"},{"id":"https://openalex.org/G801392886","display_name":null,"funder_award_id":"62073241,62173250","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/F4320327803","display_name":"Shanghai Rising-Star Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1965633385","https://openalex.org/W1978557022","https://openalex.org/W2024303516","https://openalex.org/W2037025184","https://openalex.org/W2146682436","https://openalex.org/W2148439597","https://openalex.org/W2484646121","https://openalex.org/W2582215815","https://openalex.org/W2783963839","https://openalex.org/W2800797998","https://openalex.org/W2954093458","https://openalex.org/W2996522055","https://openalex.org/W3035782080","https://openalex.org/W3047879910","https://openalex.org/W3090037761","https://openalex.org/W3161426377","https://openalex.org/W3201312234","https://openalex.org/W4200633647","https://openalex.org/W4304480072"],"related_works":["https://openalex.org/W2057376130","https://openalex.org/W2091926052","https://openalex.org/W2066807010","https://openalex.org/W2352258019","https://openalex.org/W4248803515","https://openalex.org/W3037033265","https://openalex.org/W2124277904","https://openalex.org/W4220855336","https://openalex.org/W2902449143","https://openalex.org/W4308732150"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,59],"model-free":[4],"reinforcement":[5],"learning":[6],"approach":[7],"to":[8,29,33,63,75],"obtain":[9],"the":[10,15,21,30,38,45,65,84,87],"optimal":[11,31],"capture":[12,26],"strategy":[13],"in":[14,37],"pursuit-evasion":[16],"(PE)":[17],"game.":[18],"We":[19],"present":[20],"necessary":[22],"condition":[23],"for":[24],"successful":[25],"and":[27,57],"converge":[28],"solution":[32],"achieve":[34],"Nash":[35],"equilibrium":[36],"game":[39,66],"through":[40],"online":[41],"policy":[42],"iteration,":[43],"without":[44],"prior":[46],"knowledge":[47],"of":[48,86],"pursuers'":[49],"system":[50],"dynamics.":[51],"The":[52],"multiplayer":[53],"situation":[54],"is":[55,73],"considered":[56],"employ":[58],"bipartite":[60],"graph":[61],"framework":[62],"describe":[64],"performance":[67],"index.":[68],"A":[69],"maximum":[70],"matching":[71],"algorithm":[72],"utilized":[74],"minimize":[76],"associated":[77],"cost.":[78],"Through":[79],"simulation":[80],"experiments,":[81],"we":[82],"demonstrate":[83],"effectiveness":[85],"designed":[88],"control":[89],"strategy.":[90]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}