{"id":"https://openalex.org/W4405022529","doi":"https://doi.org/10.1109/tcns.2024.3511400","title":"Distributed Multiagent Reinforcement Learning With One-Hop Neighbors and Compute Straggler Mitigation","display_name":"Distributed Multiagent Reinforcement Learning With One-Hop Neighbors and Compute Straggler Mitigation","publication_year":2024,"publication_date":"2024-12-04","ids":{"openalex":"https://openalex.org/W4405022529","doi":"https://doi.org/10.1109/tcns.2024.3511400"},"language":"en","primary_location":{"id":"doi:10.1109/tcns.2024.3511400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcns.2024.3511400","pdf_url":null,"source":{"id":"https://openalex.org/S2502544478","display_name":"IEEE Transactions on Control of Network Systems","issn_l":"2325-5870","issn":["2325-5870","2372-2533"],"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 Control of Network Systems","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":"https://openalex.org/A5017869089","display_name":"Baoqian Wang","orcid":"https://orcid.org/0000-0002-1977-5100"},"institutions":[{"id":"https://openalex.org/I1295339012","display_name":"Boeing (United States)","ror":"https://ror.org/04sm5zn07","country_code":"US","type":"company","lineage":["https://openalex.org/I1295339012"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baoqian Wang","raw_affiliation_strings":["Boeing AI, The Boeing Company, Huntsville, AL, USA"],"raw_orcid":"https://orcid.org/0000-0002-1977-5100","affiliations":[{"raw_affiliation_string":"Boeing AI, The Boeing Company, Huntsville, AL, USA","institution_ids":["https://openalex.org/I1295339012"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063416695","display_name":"Junfei Xie","orcid":"https://orcid.org/0000-0001-7406-3221"},"institutions":[{"id":"https://openalex.org/I26538001","display_name":"San Diego State University","ror":"https://ror.org/0264fdx42","country_code":"US","type":"education","lineage":["https://openalex.org/I26538001"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junfei Xie","raw_affiliation_strings":["Department of Electrical and Computer Engineering, San Diego State University, San Diego, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7406-3221","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, San Diego State University, San Diego, CA, USA","institution_ids":["https://openalex.org/I26538001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066400889","display_name":"Nikolay Atanasov","orcid":"https://orcid.org/0000-0003-0272-7580"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolay Atanasov","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0272-7580","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22476154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"2","first_page":"1300","last_page":"1312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12546","display_name":"Smart Parking Systems Research","score":0.8914999961853027,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T12546","display_name":"Smart Parking Systems Research","score":0.8914999961853027,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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":0.8535000085830688,"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":0.8068000078201294,"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/computer-science","display_name":"Computer science","score":0.6615249514579773},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5730854272842407},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.47002363204956055},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.44408348202705383},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.39167359471321106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3011956214904785}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6615249514579773},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5730854272842407},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.47002363204956055},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44408348202705383},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.39167359471321106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3011956214904785}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcns.2024.3511400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcns.2024.3511400","pdf_url":null,"source":{"id":"https://openalex.org/S2502544478","display_name":"IEEE Transactions on Control of Network Systems","issn_l":"2325-5870","issn":["2325-5870","2372-2533"],"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 Control of Network Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G479547996","display_name":null,"funder_award_id":"N00014-23-1-2353","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W1641379095","https://openalex.org/W1788292158","https://openalex.org/W2108603792","https://openalex.org/W2127908002","https://openalex.org/W2128765501","https://openalex.org/W2268702383","https://openalex.org/W2475651303","https://openalex.org/W2617547828","https://openalex.org/W2742439621","https://openalex.org/W2922342388","https://openalex.org/W3134098930","https://openalex.org/W3174406242","https://openalex.org/W3205679268","https://openalex.org/W4221145105","https://openalex.org/W4225632041","https://openalex.org/W4226071977","https://openalex.org/W4236536374","https://openalex.org/W6636881020","https://openalex.org/W6679154944","https://openalex.org/W6679393576","https://openalex.org/W6692846177","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6743684298","https://openalex.org/W6747941106","https://openalex.org/W6749032143","https://openalex.org/W6749257597","https://openalex.org/W6749304979","https://openalex.org/W6755069753","https://openalex.org/W6762491519","https://openalex.org/W6771232374","https://openalex.org/W6771904302","https://openalex.org/W6777027380","https://openalex.org/W6849717179"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Most":[0],"multiagent":[1,57],"reinforcement":[2,58],"learning":[3,59,107,128,173,185,215],"(MARL)":[4],"methods":[5],"are":[6,148],"limited":[7],"in":[8,220],"the":[9,21,29,36,72,81,106,134,163,181,184,206,212,221],"scale":[10],"of":[11,19,23,74,183,208,223],"problems":[12],"they":[13],"can":[14],"handle.":[15],"With":[16],"increasing":[17],"numbers":[18,117],"agents,":[20],"number":[22,207],"training":[24,113,135,196,218],"iterations":[25],"required":[26],"to":[27,35,83,124,130,153,179,187],"find":[28],"optimal":[30],"behaviors":[31],"increases":[32],"exponentially":[33,37],"due":[34,152],"growing":[38],"joint":[39],"state":[40],"and":[41,89,97,118,202],"action":[42],"spaces.":[43],"This":[44,120],"article":[45],"tackles":[46],"this":[47],"limitation":[48],"by":[49,76,112],"introducing":[50],"a":[51,101,126,169],"scalable":[52,204],"MARL":[53],"method":[54,69],"called":[55],"distributed":[56,127,172,214],"with":[60,114],"one-hop":[61,84,102],"neighbors":[62,85],"(DARL1N).":[63],"DARL1N":[64,193],"is":[65,203],"an":[66],"off-policy":[67],"actor\u2013critic":[68],"that":[70,192],"addresses":[71],"curse":[73],"dimensionality":[75],"restricting":[77],"information":[78],"exchanges":[79],"among":[80],"agents":[82,209],"when":[86],"representing":[87],"value":[88,96],"policy":[90,98,200],"functions.":[91],"Each":[92],"agent":[93],"optimizes":[94],"its":[95],"functions":[99],"over":[100],"neighborhood,":[103],"significantly":[104,194],"reducing":[105],"complexity,":[108],"yet":[109],"maintaining":[110],"expressiveness":[111],"varying":[115],"neighbor":[116],"states.":[119],"structure":[121],"allows":[122],"us":[123],"formulate":[125],"framework":[129],"further":[131],"speed":[132],"up":[133],"procedure.":[136],"Distributed":[137],"computing":[138],"systems,":[139],"however,":[140],"contain":[141],"<italic":[142],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[143],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">straggler</i>":[144],"compute":[145],"nodes,":[146],"which":[147,175],"slow":[149],"or":[150,158],"unresponsive":[151],"communication":[154],"bottlenecks,":[155],"software":[156],"problems,":[157],"hardware":[159],"problems.":[160],"To":[161],"mitigate":[162],"detrimental":[164],"straggler":[165],"effect,":[166],"we":[167],"introduce":[168],"novel":[170],"coded":[171,213],"architecture,":[174],"leverages":[176],"coding":[177],"theory":[178],"improve":[180],"resilience":[182],"system":[186],"stragglers.":[188,224],"Comprehensive":[189],"experiments":[190],"show":[191],"reduces":[195],"time":[197],"without":[198],"sacrificing":[199],"quality":[201],"as":[205],"increases.":[210],"Moreover,":[211],"architecture":[216],"improves":[217],"efficiency":[219],"presence":[222]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}