{"id":"https://openalex.org/W3092429416","doi":"https://doi.org/10.1109/tnnls.2020.3025711","title":"Learning Automata-Based Multiagent Reinforcement Learning for Optimization of Cooperative Tasks","display_name":"Learning Automata-Based Multiagent Reinforcement Learning for Optimization of Cooperative Tasks","publication_year":2020,"publication_date":"2020-10-07","ids":{"openalex":"https://openalex.org/W3092429416","doi":"https://doi.org/10.1109/tnnls.2020.3025711","mag":"3092429416","pmid":"https://pubmed.ncbi.nlm.nih.gov/33027003"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.3025711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3025711","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/A5100390176","display_name":"Zhen Zhang","orcid":"https://orcid.org/0000-0002-6615-629X"},"institutions":[{"id":"https://openalex.org/I108688024","display_name":"Qingdao University","ror":"https://ror.org/021cj6z65","country_code":"CN","type":"education","lineage":["https://openalex.org/I108688024"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhen Zhang","raw_affiliation_strings":["School of Automation, Qingdao University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-6615-629X","affiliations":[{"raw_affiliation_string":"School of Automation, Qingdao University, Qingdao, China","institution_ids":["https://openalex.org/I108688024"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100670772","display_name":"Dongqing Wang","orcid":"https://orcid.org/0000-0001-8856-4289"},"institutions":[{"id":"https://openalex.org/I108688024","display_name":"Qingdao University","ror":"https://ror.org/021cj6z65","country_code":"CN","type":"education","lineage":["https://openalex.org/I108688024"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongqing Wang","raw_affiliation_strings":["School of Electrical Engineering, Qingdao University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-8856-4289","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Qingdao University, Qingdao, China","institution_ids":["https://openalex.org/I108688024"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101566378","display_name":"Junwei Gao","orcid":"https://orcid.org/0000-0001-8870-2960"},"institutions":[{"id":"https://openalex.org/I108688024","display_name":"Qingdao University","ror":"https://ror.org/021cj6z65","country_code":"CN","type":"education","lineage":["https://openalex.org/I108688024"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junwei Gao","raw_affiliation_strings":["School of Automation, Qingdao University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-8870-2960","affiliations":[{"raw_affiliation_string":"School of Automation, Qingdao University, Qingdao, China","institution_ids":["https://openalex.org/I108688024"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100390176"],"corresponding_institution_ids":["https://openalex.org/I108688024"],"apc_list":null,"apc_paid":null,"fwci":9.3879,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.98224096,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"32","issue":"10","first_page":"4639","last_page":"4652"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9994000196456909,"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/T12288","display_name":"Optimization and Search Problems","score":0.9994000196456909,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9969000220298767,"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/T11182","display_name":"Auction Theory and Applications","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/learning-automata","display_name":"Learning automata","score":0.8660153746604919},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7484747171401978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.737089991569519},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.5893704295158386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46965089440345764},{"id":"https://openalex.org/keywords/quantum-finite-automata","display_name":"Quantum finite automata","score":0.4313158690929413},{"id":"https://openalex.org/keywords/automata-theory","display_name":"Automata theory","score":0.3900698721408844},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3516674041748047},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3239870071411133},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.172730952501297}],"concepts":[{"id":"https://openalex.org/C2776807809","wikidata":"https://www.wikidata.org/wiki/Q6510160","display_name":"Learning automata","level":3,"score":0.8660153746604919},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7484747171401978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737089991569519},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.5893704295158386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46965089440345764},{"id":"https://openalex.org/C174327141","wikidata":"https://www.wikidata.org/wiki/Q176837","display_name":"Quantum finite automata","level":4,"score":0.4313158690929413},{"id":"https://openalex.org/C116248031","wikidata":"https://www.wikidata.org/wiki/Q214526","display_name":"Automata theory","level":3,"score":0.3900698721408844},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3516674041748047},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3239870071411133},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.172730952501297}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2020.3025711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3025711","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:33027003","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33027003","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":[],"awards":[{"id":"https://openalex.org/G209715934","display_name":null,"funder_award_id":"61573205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4538573035","display_name":null,"funder_award_id":"ZR2019MF063","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G5923272380","display_name":null,"funder_award_id":"61903209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7842913808","display_name":null,"funder_award_id":"61873138","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"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W33871791","https://openalex.org/W83615861","https://openalex.org/W126328993","https://openalex.org/W1192553058","https://openalex.org/W1484561372","https://openalex.org/W1514633502","https://openalex.org/W1524682200","https://openalex.org/W1540725368","https://openalex.org/W1574700590","https://openalex.org/W1607392272","https://openalex.org/W1840599614","https://openalex.org/W1850230604","https://openalex.org/W2024319865","https://openalex.org/W2045817941","https://openalex.org/W2070963703","https://openalex.org/W2083535091","https://openalex.org/W2085366587","https://openalex.org/W2086977346","https://openalex.org/W2099618002","https://openalex.org/W2104602264","https://openalex.org/W2105643086","https://openalex.org/W2120327309","https://openalex.org/W2120846115","https://openalex.org/W2122115987","https://openalex.org/W2124152208","https://openalex.org/W2138362680","https://openalex.org/W2141837602","https://openalex.org/W2145067550","https://openalex.org/W2148825261","https://openalex.org/W2158029347","https://openalex.org/W2169194711","https://openalex.org/W2180467047","https://openalex.org/W2203377304","https://openalex.org/W2338351427","https://openalex.org/W2464858197","https://openalex.org/W2472826493","https://openalex.org/W2504148212","https://openalex.org/W2531287176","https://openalex.org/W2563264440","https://openalex.org/W2606378794","https://openalex.org/W2755199268","https://openalex.org/W2783021756","https://openalex.org/W2888996021","https://openalex.org/W2898680164","https://openalex.org/W2898993886","https://openalex.org/W2925477530","https://openalex.org/W2962910407","https://openalex.org/W2962938168","https://openalex.org/W2963407617","https://openalex.org/W2969419629","https://openalex.org/W2972604073","https://openalex.org/W3010758700","https://openalex.org/W3105048218","https://openalex.org/W4246615751","https://openalex.org/W4254229309","https://openalex.org/W6630755865","https://openalex.org/W6636288269","https://openalex.org/W6672070530","https://openalex.org/W6675811377","https://openalex.org/W6678168664","https://openalex.org/W6680197816","https://openalex.org/W6681342480","https://openalex.org/W6681723013","https://openalex.org/W6683289773","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W7011621630"],"related_works":["https://openalex.org/W576785828","https://openalex.org/W2049315791","https://openalex.org/W2087949151","https://openalex.org/W2953483754","https://openalex.org/W2963823488","https://openalex.org/W2058117339","https://openalex.org/W2012286375","https://openalex.org/W1977193848","https://openalex.org/W2321667159","https://openalex.org/W2299990356"],"abstract_inverted_index":{"Multiagent":[0],"reinforcement":[1],"learning":[2,52,68,100,121,131,227],"(MARL)":[3],"has":[4],"been":[5,82,104],"extensively":[6],"used":[7,33],"in":[8,26,72,182,212,224],"many":[9],"applications":[10],"for":[11,106,123],"its":[12],"tractable":[13],"implementation":[14],"and":[15,74,93,112,159,193,219],"task":[16],"distribution.":[17],"Learning":[18,45,79],"automata,":[19],"which":[20],"can":[21],"be":[22,77],"classified":[23],"under":[24],"MARL":[25],"the":[27,36,48,61,139,154,168,178,201,215,221],"category":[28],"of":[29,43,63,108,125,177,180,191,210,214,226],"independent":[30],"learner,":[31],"are":[32,70,173],"to":[34,59,76,84,134,141],"obtain":[35],"optimal":[37,170,203],"joint":[38,171,204],"action":[39,62],"or":[40],"some":[41],"type":[42],"equilibrium.":[44],"automata":[46,53,69,80,122,132],"have":[47,81,103],"following":[49],"advantages.":[50],"First,":[51],"do":[54],"not":[55],"require":[56],"any":[57,64],"agent":[58],"observe":[60],"other":[65,222],"agent.":[66],"Second,":[67],"simple":[71],"structure":[73],"easy":[75],"implemented.":[78],"applied":[83],"function":[85],"optimization,":[86],"image":[87],"processing,":[88],"data":[89],"clustering,":[90],"recommender":[91],"systems,":[92],"wireless":[94],"sensor":[95],"networks.":[96],"However,":[97],"a":[98,142,207],"few":[99],"automata-based":[101],"algorithms":[102,223],"proposed":[105],"optimization":[107,124],"cooperative":[109,126,135,183,217],"repeated":[110,184],"games":[111,185],"stochastic":[113],"games.":[114],"We":[115],"propose":[116],"an":[117,146,187],"algorithm":[118],"known":[119],"as":[120],"agents":[127],"(LA-OCA).":[128],"To":[129],"make":[130],"applicable":[133],"tasks,":[136],"we":[137],"transform":[138],"environment":[140],"P-model":[143],"by":[144],"introducing":[145],"indicator":[147],"variable":[148],"whose":[149],"value":[150],"is":[151,157,160],"one":[152],"when":[153],"maximal":[155],"reward":[156],"obtained":[158],"zero":[161],"otherwise.":[162],"Theoretical":[163],"analysis":[164],"shows":[165],"that":[166,198],"all":[167,213],"strict":[169],"actions":[172],"stable":[174],"critical":[175],"points":[176],"model":[179],"LA-OCA":[181,199],"with":[186,206],"arbitrary":[188],"finite":[189],"number":[190],"players":[192],"actions.":[194],"Simulation":[195],"results":[196],"show":[197],"obtains":[200],"pure":[202],"strategy":[205],"success":[208],"rate":[209],"100%":[211],"three":[216],"tasks":[218],"outperforms":[220],"terms":[225],"speed.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":12}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}