{"id":"https://openalex.org/W3153573172","doi":"https://doi.org/10.1109/tnnls.2021.3070584","title":"Multiagent Meta-Reinforcement Learning for Adaptive Multipath Routing Optimization","display_name":"Multiagent Meta-Reinforcement Learning for Adaptive Multipath Routing Optimization","publication_year":2021,"publication_date":"2021-04-22","ids":{"openalex":"https://openalex.org/W3153573172","doi":"https://doi.org/10.1109/tnnls.2021.3070584","mag":"3153573172","pmid":"https://pubmed.ncbi.nlm.nih.gov/33881997"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3070584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3070584","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/A5100336395","display_name":"Long Chen","orcid":"https://orcid.org/0000-0002-3272-8667"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Long Chen","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3272-8667","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016980595","display_name":"Bin Hu","orcid":"https://orcid.org/0000-0002-8851-4561"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Hu","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-8851-4561","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043199495","display_name":"Zhi\u2010Hong Guan","orcid":"https://orcid.org/0000-0001-7997-0314"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi-Hong Guan","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-7997-0314","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100765829","display_name":"Lian Zhao","orcid":"https://orcid.org/0000-0002-5602-1738"},"institutions":[{"id":"https://openalex.org/I530967","display_name":"Toronto Metropolitan University","ror":"https://ror.org/05g13zd79","country_code":"CA","type":"education","lineage":["https://openalex.org/I530967"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lian Zhao","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering, Ryerson University, Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5602-1738","affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering, Ryerson University, Toronto, Canada","institution_ids":["https://openalex.org/I530967"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100773343","display_name":"Xuemin Shen","orcid":"https://orcid.org/0000-0002-4140-287X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xuemin Shen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, Canada"],"raw_orcid":"https://orcid.org/0000-0002-4140-287X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100336395"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":7.687,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.97546044,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"33","issue":"10","first_page":"5374","last_page":"5386"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9860000014305115,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.8623471260070801},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7686784267425537},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5714352130889893},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5448125004768372},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5365922451019287},{"id":"https://openalex.org/keywords/multipath-routing","display_name":"Multipath routing","score":0.509641170501709},{"id":"https://openalex.org/keywords/adaptive-routing","display_name":"Adaptive routing","score":0.49199649691581726},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.48249387741088867},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4585130214691162},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.45514634251594543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3634924292564392},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3125203847885132},{"id":"https://openalex.org/keywords/dynamic-source-routing","display_name":"Dynamic Source Routing","score":0.3064388632774353},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.27073660492897034},{"id":"https://openalex.org/keywords/routing-protocol","display_name":"Routing protocol","score":0.2643928825855255},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09601283073425293}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8623471260070801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686784267425537},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5714352130889893},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5448125004768372},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5365922451019287},{"id":"https://openalex.org/C76522221","wikidata":"https://www.wikidata.org/wiki/Q5035396","display_name":"Multipath routing","level":5,"score":0.509641170501709},{"id":"https://openalex.org/C24856439","wikidata":"https://www.wikidata.org/wiki/Q352483","display_name":"Adaptive routing","level":5,"score":0.49199649691581726},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.48249387741088867},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4585130214691162},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.45514634251594543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3634924292564392},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3125203847885132},{"id":"https://openalex.org/C9659607","wikidata":"https://www.wikidata.org/wiki/Q1268903","display_name":"Dynamic Source Routing","level":4,"score":0.3064388632774353},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.27073660492897034},{"id":"https://openalex.org/C104954878","wikidata":"https://www.wikidata.org/wiki/Q1648707","display_name":"Routing protocol","level":3,"score":0.2643928825855255},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09601283073425293},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3070584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3070584","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:33881997","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33881997","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":[{"id":"https://metadata.un.org/sdg/16","score":0.550000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1167451160","display_name":null,"funder_award_id":"61873287","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1743199603","display_name":null,"funder_award_id":"61633011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2994175203","display_name":null,"funder_award_id":"61772086","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5614678163","display_name":null,"funder_award_id":"61976099","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7397709506","display_name":null,"funder_award_id":"61976100","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":49,"referenced_works":["https://openalex.org/W1562069137","https://openalex.org/W1984588901","https://openalex.org/W2027215167","https://openalex.org/W2030542702","https://openalex.org/W2054823577","https://openalex.org/W2076063813","https://openalex.org/W2088956500","https://openalex.org/W2096774592","https://openalex.org/W2117368434","https://openalex.org/W2130509337","https://openalex.org/W2139827365","https://openalex.org/W2145339207","https://openalex.org/W2148662748","https://openalex.org/W2154965732","https://openalex.org/W2163907500","https://openalex.org/W2310249834","https://openalex.org/W2604436698","https://openalex.org/W2758268470","https://openalex.org/W2767456812","https://openalex.org/W2768254111","https://openalex.org/W2783057440","https://openalex.org/W2800117004","https://openalex.org/W2885078078","https://openalex.org/W2896473228","https://openalex.org/W2896879375","https://openalex.org/W2898365018","https://openalex.org/W2905658145","https://openalex.org/W2908792745","https://openalex.org/W2927073559","https://openalex.org/W2943717074","https://openalex.org/W2964331420","https://openalex.org/W2971438806","https://openalex.org/W3048983622","https://openalex.org/W3150570724","https://openalex.org/W4214717370","https://openalex.org/W4241499524","https://openalex.org/W4249510973","https://openalex.org/W6681404798","https://openalex.org/W6682459407","https://openalex.org/W6729433768","https://openalex.org/W6731982132","https://openalex.org/W6733662072","https://openalex.org/W6736057607","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6744749404","https://openalex.org/W6749032143","https://openalex.org/W6750254146","https://openalex.org/W6846392434"],"related_works":["https://openalex.org/W2059194531","https://openalex.org/W1604153611","https://openalex.org/W2157538834","https://openalex.org/W2161730546","https://openalex.org/W2538421936","https://openalex.org/W2251995179","https://openalex.org/W2181914760","https://openalex.org/W2419435095","https://openalex.org/W2082566976","https://openalex.org/W2894179516"],"abstract_inverted_index":{"In":[0,28],"this":[1],"article,":[2],"we":[3,81],"investigate":[4],"the":[5,30,46,63,103,122,133,142,146],"routing":[6,31,135],"problem":[7,32],"of":[8,48,77,124,145],"packet":[9],"networks":[10],"through":[11],"multiagent":[12,38,86,90,96],"reinforcement":[13],"learning":[14,71],"(RL),":[15],"which":[16],"is":[17,33,52,118],"a":[18,36,49,69],"very":[19],"challenging":[20],"topic":[21],"in":[22,128],"distributed":[23,115],"and":[24,79,95,108,126],"autonomous":[25],"networked":[26,37],"systems.":[27],"specific,":[29],"modeled":[34],"as":[35],"partially":[39],"observable":[40],"Markov":[41],"decision":[42],"process":[43],"(MDP).":[44],"Since":[45],"MDP":[47],"network":[50,64,104],"node":[51],"not":[53],"only":[54],"affected":[55],"by":[56,74],"its":[57],"neighboring":[58],"nodes'":[59],"policies":[60],"but":[61],"also":[62],"traffic":[65,110],"demand,":[66,111],"it":[67],"becomes":[68],"multitask":[70],"problem.":[72],"Inspired":[73],"recent":[75],"success":[76],"RL":[78,87],"metalearning,":[80],"propose":[82],"two":[83],"novel":[84],"model-free":[85],"algorithms,":[88],"named":[89],"proximal":[91],"policy":[92,98],"optimization":[93,99,136],"(MAPPO)":[94],"metaproximal":[97],"(meta-MAPPO),":[100],"to":[101],"optimize":[102],"performances":[105,144],"under":[106],"fixed":[107],"time-varying":[109],"respectively.":[112],"A":[113],"practicable":[114],"implementation":[116],"framework":[117],"designed":[119],"based":[120],"on":[121],"separability":[123],"exploration":[125],"exploitation":[127],"training":[129],"MAPPO.":[130],"Compared":[131],"with":[132],"existing":[134],"policies,":[137],"our":[138],"simulation":[139],"results":[140],"demonstrate":[141],"excellent":[143],"proposed":[147],"algorithms.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":9},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-10T00:00:00"}