{"id":"https://openalex.org/W4416750233","doi":"https://doi.org/10.1109/iros60139.2025.11246236","title":"Emergent Cooperative Strategies for Pursuit-Evasion in Cluttered Environments: A Knowledge-Enhanced Multi-Agent Deep Reinforcement Learning Approach","display_name":"Emergent Cooperative Strategies for Pursuit-Evasion in Cluttered Environments: A Knowledge-Enhanced Multi-Agent Deep Reinforcement Learning Approach","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750233","doi":"https://doi.org/10.1109/iros60139.2025.11246236"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5048578575","display_name":"Yihao Sun","orcid":"https://orcid.org/0000-0002-3997-1272"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yihao Sun","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China,410073"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China,410073","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033079705","display_name":"Chao Yan","orcid":"https://orcid.org/0000-0002-2691-7955"},"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":"Chao Yan","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,College of Automation Engineering,Nanjing,China,211106"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,College of Automation Engineering,Nanjing,China,211106","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075195709","display_name":"Han Zhou","orcid":"https://orcid.org/0009-0008-9595-219X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Zhou","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China,410073"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China,410073","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110756568","display_name":"Xiaojia Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojia Xiang","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China,410073"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China,410073","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079667048","display_name":"Jie Jiang","orcid":"https://orcid.org/0000-0001-9666-815X"},"institutions":[{"id":"https://openalex.org/I68581759","display_name":"China Academy of Launch Vehicle Technology","ror":"https://ror.org/012z62f48","country_code":"CN","type":"facility","lineage":["https://openalex.org/I68581759"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Jiang","raw_affiliation_strings":["China Academy of Launch Vehicle Technology,Beijing,China,100076"],"affiliations":[{"raw_affiliation_string":"China Academy of Launch Vehicle Technology,Beijing,China,100076","institution_ids":["https://openalex.org/I68581759"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048578575"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43992126,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17138","last_page":"17145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.9677000045776367,"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":0.9677000045776367,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.008799999952316284,"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"}},{"id":"https://openalex.org/T13371","display_name":"Military Defense Systems Analysis","score":0.003000000026077032,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7592999935150146},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5401999950408936},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5249999761581421},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5239999890327454},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.39910000562667847},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3986999988555908}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7592999935150146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6521000266075134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6064000129699707},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5401999950408936},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5239999890327454},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30000001192092896},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2678999900817871}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2012518714","https://openalex.org/W2113286054","https://openalex.org/W2617547828","https://openalex.org/W2743150096","https://openalex.org/W2758653969","https://openalex.org/W2768629321","https://openalex.org/W2946040522","https://openalex.org/W3034257692","https://openalex.org/W3035829937","https://openalex.org/W3093345403","https://openalex.org/W3162743497","https://openalex.org/W4210421084","https://openalex.org/W4213246061","https://openalex.org/W4221155562","https://openalex.org/W4304480790","https://openalex.org/W4308499079","https://openalex.org/W4312354772","https://openalex.org/W4312987110","https://openalex.org/W4320176201","https://openalex.org/W4321608219","https://openalex.org/W4321763414","https://openalex.org/W4383108558","https://openalex.org/W4389665593","https://openalex.org/W4399800787","https://openalex.org/W4399981396","https://openalex.org/W4401113667","https://openalex.org/W4405394947","https://openalex.org/W4407449470"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"(DRL)":[3],"has":[4],"recently":[5],"emerged":[6],"as":[7,54],"a":[8,37,55,83,107],"promising":[9],"tool":[10],"for":[11,41],"tackling":[12],"pursuit-evasion":[13,43],"tasks.":[14],"However,":[15],"most":[16],"existing":[17],"DRL-based":[18],"pursuit":[19,50,103,124],"approaches":[20],"still":[21],"rely":[22],"on":[23],"individual":[24,138],"rewards":[25],"and":[26,78,145,151],"struggle":[27],"with":[28],"complex":[29,45],"scenarios.":[30],"To":[31],"address":[32],"these":[33],"challenges,":[34],"we":[35],"propose":[36],"knowledge-enhanced":[38],"DRL":[39],"approach":[40],"multi-agent":[42,87],"in":[44],"environments.":[46],"Specifically,":[47],"the":[48,67,101,122,131,149,154,162],"cooperative":[49,102,123,159],"problem":[51],"is":[52,71,96],"modeled":[53],"decentralized":[56],"partially":[57],"observable":[58],"Markov":[59],"decision":[60],"process":[61],"from":[62,115,137],"each":[63],"pursuers":[64],"perspective,":[65],"where":[66],"team":[68,80],"reward":[69],"function":[70],"elaborately":[72],"designed":[73],"to":[74,98],"encourage":[75],"collaborative":[76],"behavior":[77],"enhance":[79],"coordination.":[81],"Then,":[82],"novel":[84],"knowledge":[85,108],"enhanced":[86],"twin":[88],"delayed":[89],"deep":[90],"deterministic":[91],"policy":[92,125],"gradient":[93],"(KE-MATD3)":[94],"algorithm":[95],"presented":[97],"efficiently":[99],"learn":[100],"policy.":[104],"By":[105],"integrating":[106],"enhancement":[109],"mechanism":[110],"that":[111,134],"extracts":[112],"effective":[113],"information":[114],"an":[116],"improved":[117],"artificial":[118],"potential":[119],"field":[120],"method,":[121],"achieves":[126],"more":[127],"robust":[128],"convergence,":[129],"mitigating":[130],"local":[132],"optima":[133],"typically":[135],"arise":[136],"reward-based":[139],"learning.":[140],"Finally,":[141],"extensive":[142],"numerical":[143],"simulations":[144],"real-world":[146],"experiments":[147],"validate":[148],"efficiency":[150],"superiority":[152],"of":[153],"proposed":[155],"approach,":[156],"demonstrating":[157],"emergent":[158],"behaviors":[160],"among":[161],"pursuers.":[163]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}