{"id":"https://openalex.org/W4413248499","doi":"https://doi.org/10.1142/s021759592540010x","title":"Localized Multi-Agent Reinforcement Learning for Cooperative Management of Supply Chains","display_name":"Localized Multi-Agent Reinforcement Learning for Cooperative Management of Supply Chains","publication_year":2025,"publication_date":"2025-08-08","ids":{"openalex":"https://openalex.org/W4413248499","doi":"https://doi.org/10.1142/s021759592540010x"},"language":"en","primary_location":{"id":"doi:10.1142/s021759592540010x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s021759592540010x","pdf_url":null,"source":{"id":"https://openalex.org/S1254427","display_name":"Asia Pacific Journal of Operational Research","issn_l":"0217-5959","issn":["0217-5959","1793-7019"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Asia-Pacific Journal of Operational Research","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/A5026784653","display_name":"Rongjinzi Wang","orcid":"https://orcid.org/0000-0001-5736-0822"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongjinzi Wang","raw_affiliation_strings":["College of Engineering, Peking University, Beijing 100871, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Peking University, Beijing 100871, P. R. China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062949443","display_name":"Ruiyang Jin","orcid":"https://orcid.org/0000-0003-1486-9930"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Ruiyang Jin","raw_affiliation_strings":["Department of Systems Engineering, City University of Hong Kong, Kowloon, Hong Kong, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering, City University of Hong Kong, Kowloon, Hong Kong, P. R. China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100612521","display_name":"Jie Song","orcid":"https://orcid.org/0000-0003-4111-2570"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Song","raw_affiliation_strings":["College of Engineering, Peking University, Beijing 100871, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Peking University, Beijing 100871, P. R. China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062949443"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":2.49,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91484851,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"42","issue":"06","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9370999932289124,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9370999932289124,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6942628026008606},{"id":"https://openalex.org/keywords/supply-chain","display_name":"Supply chain","score":0.5938839316368103},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5807356834411621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45182108879089355},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.36585575342178345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25346651673316956},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0994047224521637},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.08737489581108093},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07462888956069946}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6942628026008606},{"id":"https://openalex.org/C108713360","wikidata":"https://www.wikidata.org/wiki/Q1824206","display_name":"Supply chain","level":2,"score":0.5938839316368103},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5807356834411621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45182108879089355},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.36585575342178345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25346651673316956},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0994047224521637},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.08737489581108093},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07462888956069946}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s021759592540010x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s021759592540010x","pdf_url":null,"source":{"id":"https://openalex.org/S1254427","display_name":"Asia Pacific Journal of Operational Research","issn_l":"0217-5959","issn":["0217-5959","1793-7019"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Asia-Pacific Journal of Operational Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1450299628","display_name":null,"funder_award_id":"72131001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8670534201","display_name":null,"funder_award_id":"T2121002","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":32,"referenced_works":["https://openalex.org/W1998270617","https://openalex.org/W1998613488","https://openalex.org/W2000248128","https://openalex.org/W2001608256","https://openalex.org/W2031015092","https://openalex.org/W2042070284","https://openalex.org/W2067589005","https://openalex.org/W2070410573","https://openalex.org/W2087412156","https://openalex.org/W2099461641","https://openalex.org/W2113910661","https://openalex.org/W2147118965","https://openalex.org/W2752539101","https://openalex.org/W2785926206","https://openalex.org/W2807525283","https://openalex.org/W2938085054","https://openalex.org/W2971079059","https://openalex.org/W2991046523","https://openalex.org/W3011272463","https://openalex.org/W3018513316","https://openalex.org/W3110295293","https://openalex.org/W3118838793","https://openalex.org/W3132558922","https://openalex.org/W3145944272","https://openalex.org/W3184770056","https://openalex.org/W3209969885","https://openalex.org/W4205375500","https://openalex.org/W4206932883","https://openalex.org/W4308067623","https://openalex.org/W4313162358","https://openalex.org/W4392974747","https://openalex.org/W4400147025"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"While":[0],"reinforcement":[1,28],"learning":[2,29],"has":[3],"significant":[4,18],"applications":[5],"in":[6,122],"smart":[7],"manufacturing,":[8],"effectively":[9],"coordinating":[10],"multiple":[11],"agents":[12],"with":[13],"limited":[14],"communication":[15],"remains":[16],"a":[17,25,45],"challenge.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23,76,112],"propose":[24,77],"localized":[26,92],"multi-agent":[27],"approach":[30],"specifically":[31],"designed":[32],"for":[33],"serial":[34,124],"supply":[35,40,108,125],"chains.":[36,126],"We":[37],"formulate":[38],"the":[39,51,56,66,78,86,102,118],"chain":[41,109],"management":[42],"problem":[43],"as":[44],"Markov":[46],"decision":[47],"process":[48],"and":[49,73,94,106],"uncover":[50],"exponential":[52],"decay":[53],"property":[54],"of":[55,104,120],"[Formula:":[57,67],"see":[58,68],"text]-functions,":[59],"which":[60],"allows":[61],"each":[62],"agent":[63],"to":[64,84,116],"approximate":[65],"text]-functions":[69],"using":[70],"local":[71],"observations":[72],"communications.":[74],"Then,":[75],"scalable":[79],"natural":[80],"actor\u2013critic":[81],"(SNAC)":[82],"algorithm":[83,90],"solve":[85],"problem.":[87],"The":[88],"SNAC":[89,121],"leverages":[91],"coordination":[93],"reduces":[95],"reliance":[96],"on":[97],"global":[98],"information,":[99],"thus":[100],"addressing":[101],"challenges":[103],"large-scale":[105],"dynamic":[107],"environments.":[110],"Additionally,":[111],"conduct":[113],"numerical":[114],"experiments":[115],"demonstrate":[117],"effectiveness":[119],"managing":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}