{"id":"https://openalex.org/W7125908978","doi":"https://doi.org/10.1109/smc58881.2025.11342630","title":"Multi-Agent Reinforcement Learning Algorithm Using Dynamic OW-QMIX in Complex Supply Chain Scenarios","display_name":"Multi-Agent Reinforcement Learning Algorithm Using Dynamic OW-QMIX in Complex Supply Chain Scenarios","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125908978","doi":"https://doi.org/10.1109/smc58881.2025.11342630"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5124068819","display_name":"Zhiqi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiqi Liu","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030112673","display_name":"Prof. Qinghua Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghua Zhu","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124084761","display_name":"An Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An Zeng","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016989631","display_name":"Yuzhu Ji","orcid":"https://orcid.org/0000-0003-3589-3884"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhu Ji","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015849144","display_name":"Baoyao Yang","orcid":"https://orcid.org/0000-0001-9092-3164"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoyao Yang","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5124068819"],"corresponding_institution_ids":["https://openalex.org/I139024713"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8385038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1211","last_page":"1218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14413","display_name":"Advanced Technologies in Various Fields","score":0.1599999964237213,"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"}},"topics":[{"id":"https://openalex.org/T14413","display_name":"Advanced Technologies in Various Fields","score":0.1599999964237213,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.10689999908208847,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.09910000115633011,"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/weighting","display_name":"Weighting","score":0.8357999920845032},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8064000010490417},{"id":"https://openalex.org/keywords/supply-chain","display_name":"Supply chain","score":0.7059999704360962},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6207000017166138},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4936000108718872},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47589999437332153},{"id":"https://openalex.org/keywords/a-weighting","display_name":"A-weighting","score":0.37130001187324524}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8357999920845032},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8064000010490417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067999839782715},{"id":"https://openalex.org/C108713360","wikidata":"https://www.wikidata.org/wiki/Q1824206","display_name":"Supply chain","level":2,"score":0.7059999704360962},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6207000017166138},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47589999437332153},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45500001311302185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3817000091075897},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.37130001187324524},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33230000734329224},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.3321000039577484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C44104985","wikidata":"https://www.wikidata.org/wiki/Q492886","display_name":"Supply chain management","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2535000145435333},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4021582007408142,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2070854196","https://openalex.org/W2165567769","https://openalex.org/W3018513316","https://openalex.org/W4248269110","https://openalex.org/W4304789907","https://openalex.org/W4306755958","https://openalex.org/W4377224800","https://openalex.org/W4388714436","https://openalex.org/W4394940707","https://openalex.org/W4396859816","https://openalex.org/W4404636194"],"related_works":[],"abstract_inverted_index":{"How":[0],"to":[1,57,99,114,181],"effectively":[2],"optimize":[3],"the":[4,16,19,78,81,88,91,130,138,141,145,157,182],"operation":[5],"for":[6],"a":[7,46,63,123,150],"complex":[8,36,116,151,189,200],"supply":[9,37,117,153,159,190],"chain":[10,38,118,154,160,191],"environment":[11,155],"has":[12],"been":[13],"high":[14],"on":[15,70,137],"agenda.":[17],"Although":[18],"existing":[20],"deep":[21],"reinforcement":[22,66,185],"learning":[23,67,186],"methods":[24],"have":[25],"achieved":[26],"success":[27],"in":[28,35,42,52,87,133,140,156,188,194],"certain":[29],"applications,":[30],"they":[31],"still":[32],"face":[33],"limitations":[34],"environments,":[39],"including":[40],"difficulties":[41],"data":[43],"sharing":[44],"and":[45,111,162,169,199],"lack":[47],"of":[48,80,90],"digital":[49],"collaboration,":[50],"especially":[51,193],"multi-agent":[53,65,101,184],"systems.":[54],"In":[55],"order":[56],"meet":[58],"this":[59],"challenge,":[60],"we":[61,121],"propose":[62,122],"novel":[64],"algorithm":[68,85,109,187],"based":[69,136],"dynamic":[71,124,197],"optimistic":[72],"weights":[73],"(DO-QMIX),":[74],"aiming":[75],"at":[76],"solving":[77],"shortcomings":[79],"traditional":[82,183],"weighted":[83],"QMIX":[84],"(WQMIX)":[86],"simplicity":[89],"weighting":[92,97,106,125,131],"function.":[93],"WQMIX":[94],"employs":[95],"two":[96],"schemes":[98],"handle":[100],"issues.":[102],"However,":[103],"its":[104],"fixed":[105],"function":[107,132],"restricts":[108],"performance":[110],"hinders":[112],"adaptability":[113],"dynamic,":[115],"challenges.":[119],"Therefore,":[120],"mechanism,":[126],"which":[127],"can":[128],"adjust":[129],"real":[134],"time":[135],"changes":[139,198],"environment,":[142],"thus":[143],"improving":[144],"overall":[146],"efficiency.":[147],"We":[148],"construct":[149],"multi-stage":[152],"real-world":[158,168],"scenario":[161],"conduct":[163],"many":[164],"experiments":[165],"using":[166],"both":[167],"simulated":[170],"datasets.":[171],"The":[172],"experimental":[173],"results":[174],"demonstrate":[175],"that":[176],"DO-QMIX":[177],"is":[178],"significantly":[179],"superior":[180],"scenarios,":[192],"dealing":[195],"with":[196],"decisions.":[201]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-29T00:00:00"}