{"id":"https://openalex.org/W3106917752","doi":"https://doi.org/10.1109/icca51439.2020.9264518","title":"Multi-Agent Reinforcement Learning for Adaptive Routing: A Hybrid Method using Eligibility Traces","display_name":"Multi-Agent Reinforcement Learning for Adaptive Routing: A Hybrid Method using Eligibility Traces","publication_year":2020,"publication_date":"2020-10-09","ids":{"openalex":"https://openalex.org/W3106917752","doi":"https://doi.org/10.1109/icca51439.2020.9264518","mag":"3106917752"},"language":"en","primary_location":{"id":"doi:10.1109/icca51439.2020.9264518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","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/A5008210594","display_name":"Siliang Zeng","orcid":"https://orcid.org/0009-0002-5863-8659"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Siliang Zeng","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002053202","display_name":"Xingfei Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingfei Xu","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100419212","display_name":"Yi Chen","orcid":"https://orcid.org/0000-0001-5616-2170"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Chen","raw_affiliation_strings":["Shenzhen Research Institute of Big Data","The Chinese University of Hong Kong, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data","institution_ids":["https://openalex.org/I4210099586"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008210594"],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":1.1257,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83437059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1332","last_page":"1339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9908999800682068,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9908999800682068,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9904000163078308,"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/T10454","display_name":"Optimal Power Flow Distribution","score":0.9666000008583069,"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":0.9009944796562195},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.833055853843689},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6218724250793457},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6091575026512146},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.6040971875190735},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.49172571301460266},{"id":"https://openalex.org/keywords/adaptive-routing","display_name":"Adaptive routing","score":0.47798484563827515},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.45545002818107605},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.43528443574905396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40503132343292236},{"id":"https://openalex.org/keywords/static-routing","display_name":"Static routing","score":0.38504788279533386},{"id":"https://openalex.org/keywords/routing-protocol","display_name":"Routing protocol","score":0.3572322130203247},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33785712718963623},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2556114196777344}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9009944796562195},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.833055853843689},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6218724250793457},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6091575026512146},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.6040971875190735},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.49172571301460266},{"id":"https://openalex.org/C24856439","wikidata":"https://www.wikidata.org/wiki/Q352483","display_name":"Adaptive routing","level":5,"score":0.47798484563827515},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45545002818107605},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.43528443574905396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40503132343292236},{"id":"https://openalex.org/C204948658","wikidata":"https://www.wikidata.org/wiki/Q1119410","display_name":"Static routing","level":4,"score":0.38504788279533386},{"id":"https://openalex.org/C104954878","wikidata":"https://www.wikidata.org/wiki/Q1648707","display_name":"Routing protocol","level":3,"score":0.3572322130203247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33785712718963623},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2556114196777344},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icca51439.2020.9264518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"awards":[],"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":23,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1521427077","https://openalex.org/W1702462424","https://openalex.org/W2102655743","https://openalex.org/W2113913482","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2132940773","https://openalex.org/W2144658257","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2156666755","https://openalex.org/W2156737235","https://openalex.org/W2911407713","https://openalex.org/W4298857966","https://openalex.org/W6630994837","https://openalex.org/W6637255130","https://openalex.org/W6637967152","https://openalex.org/W6675678083","https://openalex.org/W6681404798","https://openalex.org/W6682459407","https://openalex.org/W6683195989","https://openalex.org/W6683204974"],"related_works":["https://openalex.org/W4380551608","https://openalex.org/W2142355100","https://openalex.org/W2061862411","https://openalex.org/W1985089845","https://openalex.org/W3185457588","https://openalex.org/W2138332953","https://openalex.org/W2069696496","https://openalex.org/W2551397502","https://openalex.org/W1998565297","https://openalex.org/W2183199679"],"abstract_inverted_index":{"Packet":[0],"routing":[1,119],"in":[2,45,90,120,165],"communication":[3,121],"networks":[4],"is":[5,48,159],"a":[6,55,93,102,112,136],"natural":[7],"problem":[8],"for":[9,117],"sequential":[10],"decision-making.":[11],"Previously,":[12],"many":[13,60],"heuristic":[14],"methods":[15],"are":[16,36,72,80,146],"proposed":[17,183],"based":[18],"on":[19,26],"domain":[20],"knowledge.":[21],"Most":[22],"of":[23,29,41,54,62,126],"them":[24],"rely":[25],"the":[27,30,34,39,42,52,63,78,128,132,140,166],"understanding":[28],"network":[31,57,64,70,167],"environment":[32],"and":[33,69,77,131,168],"algorithms":[35],"sensitive":[37],"to":[38,50,82,148,152,161,175],"model":[40,51],"networks.":[43],"However,":[44],"practice":[46],"it":[47],"intractable":[49],"dynamics":[53],"real":[56],"perfectly,":[58],"since":[59],"features":[61],"such":[65],"as":[66],"traffic":[67],"load":[68],"topology":[71],"irregularly":[73],"changing":[74],"with":[75,92],"time":[76],"changes":[79,164],"hard":[81],"predict.":[83],"Hence,":[84],"model-free":[85,103],"approach":[86],"becomes":[87],"more":[88],"promising":[89],"dealing":[91],"complex":[94],"dynamic":[95,163],"environment.":[96],"In":[97],"this":[98],"work,":[99],"we":[100],"consider":[101],"method":[104],"by":[105],"leveraging":[106],"reinforcement":[107,114],"learning":[108,115],"techniques.":[109],"We":[110],"propose":[111],"multi-agent":[113],"framework":[116],"adaptive":[118,173],"networks,":[122],"which":[123],"takes":[124],"advantage":[125],"both":[127],"real-time":[129],"Q-learning":[130],"actor-critic":[133],"methods.":[134],"Provided":[135],"global":[137],"feedback":[138],"signal,":[139],"routers":[141],"(agents)":[142],"act":[143],"independently":[144],"but":[145],"able":[147],"learn":[149],"cooperative":[150],"behaviors":[151],"reduce":[153],"packet":[154],"delivery":[155],"time.":[156],"Our":[157],"algorithm":[158,184],"robust":[160],"some":[162,186],"each":[169],"agent":[170],"learns":[171],"an":[172],"policy":[174],"route":[176],"packets.":[177],"Simulation":[178],"results":[179],"demonstrate":[180],"that":[181],"our":[182],"outperforms":[185],"existing":[187],"benchmark":[188],"algorithms.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}