{"id":"https://openalex.org/W4388727145","doi":"https://doi.org/10.1109/iecon51785.2023.10312136","title":"Distributed Optimal Pursuit-Evasion Strategy of Multiple-Pursuer Single-Evader Game via Reinforcement Learning","display_name":"Distributed Optimal Pursuit-Evasion Strategy of Multiple-Pursuer Single-Evader Game via Reinforcement Learning","publication_year":2023,"publication_date":"2023-10-16","ids":{"openalex":"https://openalex.org/W4388727145","doi":"https://doi.org/10.1109/iecon51785.2023.10312136"},"language":"en","primary_location":{"id":"doi:10.1109/iecon51785.2023.10312136","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iecon51785.2023.10312136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2023- 49th 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/A5106716376","display_name":"Jinrui Zhang","orcid":"https://orcid.org/0009-0005-2286-1818"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinrui Zhang","raw_affiliation_strings":["Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications,Nanjing,China","Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020669784","display_name":"Huaipin Zhang","orcid":"https://orcid.org/0000-0001-6405-1382"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaipin Zhang","raw_affiliation_strings":["Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications,Nanjing,China","Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100434523","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0001-8045-2549"},"institutions":[{"id":"https://openalex.org/I137056471","display_name":"Nanjing University of Finance and Economics","ror":"https://ror.org/031y8am81","country_code":"CN","type":"education","lineage":["https://openalex.org/I137056471"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["College of Information Engineering, Nanjing University of Finance and Economics,Nanjing,China","College of Information Engineering, Nanjing University of Finance and Economics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Information Engineering, Nanjing University of Finance and Economics,Nanjing,China","institution_ids":["https://openalex.org/I137056471"]},{"raw_affiliation_string":"College of Information Engineering, Nanjing University of Finance and Economics, Nanjing, China","institution_ids":["https://openalex.org/I137056471"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5106716376"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07583729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.9994999766349792,"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":0.9994999766349792,"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":0.998199999332428,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9617999792098999,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/pursuer","display_name":"Pursuer","score":0.9863096475601196},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8497354984283447},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.746291995048523},{"id":"https://openalex.org/keywords/pursuit-evasion","display_name":"Pursuit-evasion","score":0.7332461476325989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6751091480255127},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6520566344261169},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6385483145713806},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4889932870864868},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4867258369922638},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42985332012176514},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42527443170547485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29809117317199707},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2321297824382782}],"concepts":[{"id":"https://openalex.org/C2776927521","wikidata":"https://www.wikidata.org/wiki/Q468489","display_name":"Pursuer","level":2,"score":0.9863096475601196},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8497354984283447},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.746291995048523},{"id":"https://openalex.org/C2778388243","wikidata":"https://www.wikidata.org/wiki/Q7261573","display_name":"Pursuit-evasion","level":2,"score":0.7332461476325989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6751091480255127},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6520566344261169},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6385483145713806},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4889932870864868},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4867258369922638},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42985332012176514},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42527443170547485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29809117317199707},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2321297824382782},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iecon51785.2023.10312136","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iecon51785.2023.10312136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1501032615","https://openalex.org/W1581842928","https://openalex.org/W1844356221","https://openalex.org/W1965633385","https://openalex.org/W1968908471","https://openalex.org/W2134595317","https://openalex.org/W2162417941","https://openalex.org/W2608634483","https://openalex.org/W2615986577","https://openalex.org/W2766096873","https://openalex.org/W2767257775","https://openalex.org/W2791791691","https://openalex.org/W2805642768","https://openalex.org/W2954093458","https://openalex.org/W3000179003","https://openalex.org/W3035782080","https://openalex.org/W3132223699","https://openalex.org/W4285189613","https://openalex.org/W6683581137"],"related_works":["https://openalex.org/W2091926052","https://openalex.org/W2057376130","https://openalex.org/W4253161990","https://openalex.org/W2184611791","https://openalex.org/W2039546613","https://openalex.org/W2522390654","https://openalex.org/W114019308","https://openalex.org/W1994748888","https://openalex.org/W4390796281","https://openalex.org/W4388727145"],"abstract_inverted_index":{"In":[0,76],"this":[1],"paper,":[2],"we":[3,35,58,82],"investigate":[4],"pursuit-evasion":[5],"game":[6],"problem":[7],"for":[8,46],"multiple-pursuer":[9],"single-evader":[10],"using":[11,52],"reinforcement":[12],"learning.":[13],"A":[14],"performance":[15],"function":[16,69,92],"including":[17],"the":[18,30,37,42,47,50,53,67,89,105,108],"states":[19],"and":[20,40,49,70,93],"limited":[21],"inputs":[22],"of":[23,73,107],"all":[24,74],"players":[25],"is":[26,101],"developed":[27],"to":[28,65,78,87,103],"evaluate":[29],"whole":[31],"system's":[32],"cost.":[33],"Then":[34],"construct":[36,83],"Hamiltonian":[38],"equation":[39],"design":[41],"optimal":[43,90,94],"control":[44,71,95],"polices":[45],"pursuers":[48],"evaders":[51],"Bellman":[54],"optimization":[55],"principle.":[56],"And":[57],"present":[59],"a":[60,84,98],"policy":[61],"iteration":[62],"(PI)":[63],"algorithm":[64],"learn":[66],"value":[68,91],"policies":[72],"players.":[75],"order":[77],"implement":[79],"PI":[80],"algorithm,":[81],"neural":[85],"network":[86],"approximate":[88],"strategy.":[96],"Finally,":[97],"simulation":[99],"example":[100],"provided":[102],"demonstrate":[104],"effectiveness":[106],"algorithm.":[109]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}