{"id":"https://openalex.org/W4391991739","doi":"https://doi.org/10.1109/tnnls.2024.3362969","title":"Hierarchical Reinforcement Learning for UAV-PE Game With Alternative Delay Update Method","display_name":"Hierarchical Reinforcement Learning for UAV-PE Game With Alternative Delay Update Method","publication_year":2024,"publication_date":"2024-02-21","ids":{"openalex":"https://openalex.org/W4391991739","doi":"https://doi.org/10.1109/tnnls.2024.3362969","pmid":"https://pubmed.ncbi.nlm.nih.gov/38381648"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3362969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3362969","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/A5100652944","display_name":"Xiao Ma","orcid":"https://orcid.org/0000-0002-5705-3942"},"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":"Xiao Ma","raw_affiliation_strings":["School of Astronautics, Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334733","display_name":"Yuan Yuan","orcid":"https://orcid.org/0000-0001-7964-6514"},"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":"Yuan Yuan","raw_affiliation_strings":["School of Astronautics, Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100344279","display_name":"Lei Guo","orcid":"https://orcid.org/0000-0002-3061-2337"},"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":"Lei Guo","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100652944"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":14.4349,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.98348565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"36","issue":"3","first_page":"4639","last_page":"4651"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.9966999888420105,"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":0.9966999888420105,"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":0.9943000078201294,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9879000186920166,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8074405193328857},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.6947002410888672},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6926817893981934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6465648412704468},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5389876961708069},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.49533525109291077},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4628964960575104},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4328458905220032},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3526897728443146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3107605576515198},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2601473033428192},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23464685678482056}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8074405193328857},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.6947002410888672},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6926817893981934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6465648412704468},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5389876961708069},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49533525109291077},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4628964960575104},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4328458905220032},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3526897728443146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3107605576515198},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2601473033428192},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23464685678482056},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3362969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3362969","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:38381648","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38381648","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":[],"awards":[{"id":"https://openalex.org/G1411699173","display_name":null,"funder_award_id":"62073268","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3187690760","display_name":null,"funder_award_id":"62122063","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2027197837","https://openalex.org/W2579592432","https://openalex.org/W2735695630","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2887972911","https://openalex.org/W2964106644","https://openalex.org/W2973229164","https://openalex.org/W3016673028","https://openalex.org/W3019638220","https://openalex.org/W3085472573","https://openalex.org/W3091464182","https://openalex.org/W3109467707","https://openalex.org/W3117938601","https://openalex.org/W3119207288","https://openalex.org/W3146025840","https://openalex.org/W3174406242","https://openalex.org/W3174733757","https://openalex.org/W3193544356","https://openalex.org/W3193956784","https://openalex.org/W3207266074","https://openalex.org/W4213246061","https://openalex.org/W4221019190","https://openalex.org/W4285225935","https://openalex.org/W4285237905","https://openalex.org/W4295872207","https://openalex.org/W4311777802","https://openalex.org/W4312987110","https://openalex.org/W4313325790","https://openalex.org/W4318962928","https://openalex.org/W4321763414","https://openalex.org/W4323075742","https://openalex.org/W4323544459","https://openalex.org/W4327729182","https://openalex.org/W4361988347","https://openalex.org/W4365145144","https://openalex.org/W4380624335","https://openalex.org/W4381730133","https://openalex.org/W6747473740","https://openalex.org/W6748839928"],"related_works":["https://openalex.org/W2789522126","https://openalex.org/W2066693961","https://openalex.org/W2368363778","https://openalex.org/W122584421","https://openalex.org/W4244295168","https://openalex.org/W2753351751","https://openalex.org/W3185180338","https://openalex.org/W2889348933","https://openalex.org/W2351643838","https://openalex.org/W3033677963"],"abstract_inverted_index":{"This":[0],"article":[1,117],"proposes":[2],"a":[3,40,47,54,110],"novel":[4],"hierarchical":[5,41],"reinforcement":[6],"learning":[7,42],"(HRL)":[8],"algorithm":[9,123,207],"for":[10,128,156],"unmanned":[11],"aerial":[12],"vehicle":[13],"pursuit-evasion":[14],"(UAV-PE)":[15],"game":[16,35,49,78,106,139,190],"systems":[17,79,107,140],"with":[18,124,182],"an":[19,121,125],"alternative":[20],"delay":[21],"update":[22],"(ADU)":[23],"method.":[24,210],"In":[25,60],"the":[26,29,33,71,86,93,104,136,145,158,163,168,177,183,199,204],"proposed":[27,164,205],"algorithm,":[28],"approximate":[30,70,130],"solutions":[31,134],"of":[32,51,58,76,96,103,115,135,147,162,170,179,186,203],"UAV-PE":[34,77,105,138,189],"problem":[36],"are":[37,67,142,154,172,195],"derived":[38],"from":[39],"process,":[43],"which":[44,141],"relies":[45],"on":[46],"zero-sum":[48],"process":[50,57],"kinematics":[52,81,148,187],"and":[53,73,82,149,160,201,208],"corresponding":[55],"optimal":[56],"dynamics.":[59,150],"this":[61,116],"case,":[62],"deep":[63,97],"neural":[64],"networks":[65],"(NNs)":[66],"used":[68],"to":[69,91,108,119,144,174,197],"policy":[72],"value":[74],"functions":[75],"in":[80,188],"dynamics":[83,180],"level.":[84],"Furthermore,":[85],"ADU":[87,126,209],"method":[88,127],"is":[89,118],"adopted":[90],"improve":[92],"training":[94],"efficiency":[95],"NN":[98],"by":[99],"fixing":[100],"one":[101],"player":[102],"form":[109],"stable":[111],"environment.":[112],"The":[113],"goal":[114],"develop":[120],"HRL":[122,165,206],"obtaining":[129],"Nash":[131],"equilibrium":[132],"(NE)":[133],"considered":[137],"subjected":[143],"coupling":[146],"Subsequently,":[151],"sufficient":[152],"conditions":[153],"provided":[155,196],"analyzing":[157],"convergence":[159],"optimality":[161],"algorithm.":[166],"Moreover,":[167],"inequalities":[169],"overload":[171],"obtained":[173],"guarantee":[175],"that":[176],"state":[178],"tracks":[181],"control":[184],"input":[185],"systems.":[191],"Finally,":[192],"simulation":[193],"examples":[194],"demonstrate":[198],"feasibility":[200],"usefulness":[202]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}