{"id":"https://openalex.org/W4399154507","doi":"https://doi.org/10.1109/lcsys.2024.3407632","title":"Cooperative Multi-Agent Q-Learning Using Distributed MPC","display_name":"Cooperative Multi-Agent Q-Learning Using Distributed MPC","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399154507","doi":"https://doi.org/10.1109/lcsys.2024.3407632"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2024.3407632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2024.3407632","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","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/A5011634446","display_name":"Hossein Nejatbakhsh Esfahani","orcid":"https://orcid.org/0000-0003-3515-1645"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hossein Nejatbakhsh Esfahani","raw_affiliation_strings":["Department of Mechanical Engineering, Clemson University, Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0000-0003-3515-1645","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086596463","display_name":"Javad Mohammadpour Velni","orcid":"https://orcid.org/0000-0001-8546-221X"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Javad Mohammadpour Velni","raw_affiliation_strings":["Department of Mechanical Engineering, Clemson University, Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0000-0001-8546-221X","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I8078737"],"apc_list":null,"apc_paid":null,"fwci":1.3012,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77590023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"8","issue":null,"first_page":"2193","last_page":"2198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9922999739646912,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9922999739646912,"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/T10320","display_name":"Neural Networks and Applications","score":0.916700005531311,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4898047149181366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4898047149181366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcsys.2024.3407632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2024.3407632","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5946361117","display_name":"Collaborative Research: Distributed Predictive Control of Cold Atmospheric Microplasma Jet Arrays for Materials Processing","funder_award_id":"2302219","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W61442854","https://openalex.org/W206679605","https://openalex.org/W2028790617","https://openalex.org/W2158119718","https://openalex.org/W2888996021","https://openalex.org/W2930426397","https://openalex.org/W2949963774","https://openalex.org/W3011272463","https://openalex.org/W3025165553","https://openalex.org/W3038805052","https://openalex.org/W4205468042","https://openalex.org/W4214717370","https://openalex.org/W4297792341","https://openalex.org/W4381549394","https://openalex.org/W6762491519","https://openalex.org/W6802325372","https://openalex.org/W6853440616"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"In":[0,19,103],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,55,68],"cooperative":[6,56,106],"Multi-Agent":[7],"Reinforcement":[8],"Learning":[9],"(MARL)":[10],"approach":[11],"based":[12,29,70,116],"on":[13,30,71,117],"Distributed":[14],"Model":[15],"Predictive":[16],"Control":[17],"(DMPC).":[18],"the":[20,23,31,36,46,63,72,80,100,104,108,118,125],"proposed":[21,105],"framework,":[22],"local":[24,47,92,101],"MPC":[25],"schemes":[26],"are":[27],"formulated":[28],"dual":[32],"decomposition":[33],"method":[34],"in":[35,54,124],"context":[37],"of":[38],"DMPC":[39,64,126],"and":[40],"will":[41],"be":[42,88],"used":[43],"to":[44],"derive":[45],"state":[48,82,93],"(and":[49,83,94],"action)":[50,84,95],"value":[51,85,96],"functions":[52,86,97],"required":[53],"Q-learning":[57],"algorithm.":[58],"We":[59],"further":[60],"show":[61],"that":[62,79],"scheme":[65],"can":[66,87],"yield":[67],"framework":[69],"Value":[73],"Function":[74],"Decomposition":[75],"(VFD)":[76],"principle":[77],"so":[78],"global":[81],"decomposed":[89],"into":[90],"several":[91],"captured":[98],"from":[99],"MPCs.":[102],"MARL,":[107],"coordination":[109],"between":[110],"individual":[111],"agents":[112],"is":[113],"then":[114],"achieved":[115],"multiplier-sharing":[119],"step,":[120],"a.k.a":[121],"inter-agent":[122],"negotiation":[123],"scheme.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}