{"id":"https://openalex.org/W4410152954","doi":"https://doi.org/10.1109/tai.2025.3566069","title":"A Hierarchical Deep Reinforcement Learning Strategy for Collective Pursuit-Evasion Game With Partial Observations","display_name":"A Hierarchical Deep Reinforcement Learning Strategy for Collective Pursuit-Evasion Game With Partial Observations","publication_year":2025,"publication_date":"2025-05-07","ids":{"openalex":"https://openalex.org/W4410152954","doi":"https://doi.org/10.1109/tai.2025.3566069"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2025.3566069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3566069","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","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":null,"display_name":"Xiaoxiao Wang","orcid":"https://orcid.org/0000-0002-5528-8748"},"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":"Xiaoxiao Wang","raw_affiliation_strings":["Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5528-8748","affiliations":[{"raw_affiliation_string":"Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089663996","display_name":"Peng Yi","orcid":"https://orcid.org/0000-0002-2494-1505"},"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":"Peng Yi","raw_affiliation_strings":["Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2494-1505","affiliations":[{"raw_affiliation_string":"Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100359415","display_name":"Yiguang Hong","orcid":"https://orcid.org/0000-0001-9505-8739"},"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":"Yiguang Hong","raw_affiliation_strings":["Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9505-8739","affiliations":[{"raw_affiliation_string":"Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":3.3626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91276833,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"7","issue":"1","first_page":"76","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.9726999998092651,"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":0.9726999998092651,"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":0.9559000134468079,"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":0.7424773573875427},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5012562274932861},{"id":"https://openalex.org/keywords/evasion","display_name":"Evasion (ethics)","score":0.4781430959701538},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46362972259521484},{"id":"https://openalex.org/keywords/pursuit-evasion","display_name":"Pursuit-evasion","score":0.4382888078689575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34966981410980225},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.32207396626472473},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.16438013315200806},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0963604748249054}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7424773573875427},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5012562274932861},{"id":"https://openalex.org/C2781251061","wikidata":"https://www.wikidata.org/wiki/Q5416089","display_name":"Evasion (ethics)","level":3,"score":0.4781430959701538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46362972259521484},{"id":"https://openalex.org/C2778388243","wikidata":"https://www.wikidata.org/wiki/Q7261573","display_name":"Pursuit-evasion","level":2,"score":0.4382888078689575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34966981410980225},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32207396626472473},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.16438013315200806},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0963604748249054},{"id":"https://openalex.org/C8891405","wikidata":"https://www.wikidata.org/wiki/Q1059","display_name":"Immune system","level":2,"score":0.0},{"id":"https://openalex.org/C203014093","wikidata":"https://www.wikidata.org/wiki/Q101929","display_name":"Immunology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2025.3566069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3566069","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2424899740","display_name":null,"funder_award_id":"72271187","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8718491251","display_name":null,"funder_award_id":"62373283","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W182112988","https://openalex.org/W2055504162","https://openalex.org/W2084041087","https://openalex.org/W2088956500","https://openalex.org/W2112420033","https://openalex.org/W2160484294","https://openalex.org/W2604704722","https://openalex.org/W2747213132","https://openalex.org/W2754181951","https://openalex.org/W2954991145","https://openalex.org/W2982316857","https://openalex.org/W2996896271","https://openalex.org/W3035782080","https://openalex.org/W3035829937","https://openalex.org/W3206895809","https://openalex.org/W3208081444","https://openalex.org/W4205501012","https://openalex.org/W4225854080","https://openalex.org/W4232217679","https://openalex.org/W4280641865","https://openalex.org/W4312309366","https://openalex.org/W4313887415","https://openalex.org/W4315473069","https://openalex.org/W4315489041","https://openalex.org/W4315489393","https://openalex.org/W4321763414","https://openalex.org/W4386432078","https://openalex.org/W4386848825","https://openalex.org/W4388240445","https://openalex.org/W4389306676","https://openalex.org/W4389665593","https://openalex.org/W4391721641","https://openalex.org/W4391940985","https://openalex.org/W4394850779","https://openalex.org/W4399146345","https://openalex.org/W4400986585"],"related_works":["https://openalex.org/W2057376130","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W2091926052","https://openalex.org/W2352258019","https://openalex.org/W4248803515","https://openalex.org/W3037033265","https://openalex.org/W2124277904","https://openalex.org/W4220855336"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,21,26,48,89,93,97,108,114,134,138,143,146,157,166,185,213,216,220,227],"problem":[4],"of":[5,159,215,226],"Collective":[6,54],"Pursuit-Evasion":[7],"Game":[8,69],"(C-PEG)":[9],"with":[10],"partial":[11],"observation,":[12],"aiming":[13],"to":[14,112,153],"enhance":[15],"cooperation":[16],"among":[17],"cluster":[18,44],"pursuers,":[19],"reduce":[20],"game":[22],"space,":[23],"and":[24,46,82,96,102,110,129,145,162,202,223],"optimize":[25],"overall":[27],"pursuer":[28],"strategy":[29,140],"efficiency":[30],"in":[31,116,183,198,205,230],"complex":[32],"dynamic":[33],"environments.":[34,209],"Firstly,":[35],"we":[36,64],"consider":[37],"a":[38,53,66,170,189,199],"distributed":[39],"communication":[40],"model":[41,47],"suitable":[42],"for":[43,107,192],"collaboration":[45],"multi-agent":[49],"cooperative":[50],"task":[51],"as":[52,100],"Decentralized":[55],"Partially":[56],"Observable":[57],"Markov":[58],"Decision":[59],"Process":[60],"(C-Dec":[61],"POMDP).":[62],"Then":[63],"propose":[65],"Hierarchical":[67],"Regularization":[68],"Multi-agent":[70],"Deep":[71],"Deterministic":[72],"Policy":[73],"Gradient":[74],"(HRG-MADDPG)":[75],"algorithm,":[76],"which":[77],"includes":[78],"High-Level":[79],"Strategy":[80,84],"(HLS)":[81],"Low-Level":[83],"(LLS).":[85],"The":[86,121],"HLS":[87,144],"takes":[88],"current":[90],"observation":[91],"from":[92],"pursuers\u2019":[94,98],"sensors":[95],"status":[99],"inputs,":[101],"outputs":[103],"target":[104],"allocation":[105],"strategies":[106],"coalitions":[109],"individuals":[111],"guide":[113],"LLS":[115,122],"executing":[117],"specific":[118],"pursuit":[119],"tasks.":[120],"is":[123,180,196],"further":[124,203],"divided":[125],"into":[126],"centralized":[127,135],"training":[128,136],"decentralized":[130,167],"execution":[131,168],"phases.":[132],"In":[133,165],"phase,":[137,169],"guiding":[139],"provided":[141],"by":[142],"introduced":[147],"regularization":[148],"auxiliary":[149,163],"term":[150],"are":[151],"combined":[152],"promote":[154],"decision-making":[155],"through":[156],"fusion":[158],"favorable":[160],"situations":[161],"terms.":[164],"reliable":[171,190],"policy":[172],"improvement":[173],"method":[174,191],"based":[175],"on":[176],"partially":[177],"observable":[178],"information":[179],"designed.":[181],"All":[182],"all,":[184],"HRG-MADDPG":[186],"algorithm":[187],"provides":[188],"collective":[193],"pursuit-evasion.":[194],"It":[195],"trained":[197],"single":[200],"environment":[201],"validated":[204],"multiple":[206],"different":[207],"test":[208],"Simulation":[210],"results":[211],"confirm":[212],"effectiveness":[214],"proposed":[217,228],"method,":[218],"showing":[219],"adaptability,":[221],"scalability,":[222],"rapid":[224],"responsiveness":[225],"framework":[229],"various":[231],"practical":[232],"applications.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-08T20:05:33.558190","created_date":"2025-10-10T00:00:00"}