{"id":"https://openalex.org/W4405445209","doi":"https://doi.org/10.3390/a17120579","title":"A Multi-Agent Centralized Strategy Gradient Reinforcement Learning Algorithm Based on State Transition","display_name":"A Multi-Agent Centralized Strategy Gradient Reinforcement Learning Algorithm Based on State Transition","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4405445209","doi":"https://doi.org/10.3390/a17120579"},"language":"en","primary_location":{"id":"doi:10.3390/a17120579","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17120579","pdf_url":"https://www.mdpi.com/1999-4893/17/12/579/pdf?version=1734259962","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/17/12/579/pdf?version=1734259962","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100721966","display_name":"Lei Sheng","orcid":"https://orcid.org/0000-0002-5725-1375"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]},{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Sheng","raw_affiliation_strings":["National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha 410073, China","School of Command and Control Engineering, Army Engineering University, Nanjing 210007, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"School of Command and Control Engineering, Army Engineering University, Nanjing 210007, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026327666","display_name":"Honghui Chen","orcid":"https://orcid.org/0009-0003-5234-0592"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Honghui Chen","raw_affiliation_strings":["National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030992865","display_name":"Xiliang Chen","orcid":"https://orcid.org/0000-0001-5198-0932"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiliang Chen","raw_affiliation_strings":["School of Command and Control Engineering, Army Engineering University, Nanjing 210007, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Command and Control Engineering, Army Engineering University, Nanjing 210007, China","institution_ids":["https://openalex.org/I4210163363"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5026327666","https://openalex.org/A5030992865"],"corresponding_institution_ids":["https://openalex.org/I170215575","https://openalex.org/I4210163363"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.243,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66566674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"17","issue":"12","first_page":"579","last_page":"579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9962000250816345,"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"}},{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.9745000004768372,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8589869141578674},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6329488754272461},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5574138164520264},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41578906774520874},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3958706259727478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3689477741718292},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20089823007583618}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8589869141578674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6329488754272461},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5574138164520264},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41578906774520874},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3958706259727478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3689477741718292},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20089823007583618}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/a17120579","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17120579","pdf_url":"https://www.mdpi.com/1999-4893/17/12/579/pdf?version=1734259962","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:972010c0e91d40d3be242eefb050f166","is_oa":false,"landing_page_url":"https://doaj.org/article/972010c0e91d40d3be242eefb050f166","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 17, Iss 12, p 579 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/a17120579","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17120579","pdf_url":"https://www.mdpi.com/1999-4893/17/12/579/pdf?version=1734259962","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2409733177","display_name":null,"funder_award_id":"No. 62273356","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405445209.pdf","grobid_xml":"https://content.openalex.org/works/W4405445209.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2151210636","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2626820647","https://openalex.org/W2787938642","https://openalex.org/W2886012730","https://openalex.org/W2901645090","https://openalex.org/W2948175577","https://openalex.org/W2948210913","https://openalex.org/W2963049774","https://openalex.org/W2963762747","https://openalex.org/W3015437096","https://openalex.org/W3018906259","https://openalex.org/W3024896014","https://openalex.org/W3034257692","https://openalex.org/W3085605093","https://openalex.org/W3093524531","https://openalex.org/W3108488004","https://openalex.org/W3122460059","https://openalex.org/W3127235394","https://openalex.org/W3163926178","https://openalex.org/W3166816823","https://openalex.org/W3167419264","https://openalex.org/W3183420623","https://openalex.org/W3186672455","https://openalex.org/W3199614200","https://openalex.org/W3202847499","https://openalex.org/W3204742620","https://openalex.org/W3208045904","https://openalex.org/W3211445425","https://openalex.org/W3212348395","https://openalex.org/W3213063001","https://openalex.org/W4200042293","https://openalex.org/W4221164079","https://openalex.org/W4221167833","https://openalex.org/W4226424194","https://openalex.org/W4283830037","https://openalex.org/W4287755265","https://openalex.org/W4297900097","https://openalex.org/W4299802797","https://openalex.org/W4304789907","https://openalex.org/W4306786778","https://openalex.org/W4313598504","https://openalex.org/W4381327857","https://openalex.org/W4391919254","https://openalex.org/W4392292700","https://openalex.org/W4393241368","https://openalex.org/W6682314434","https://openalex.org/W6738796088","https://openalex.org/W6766805167","https://openalex.org/W6781750019","https://openalex.org/W6784152626","https://openalex.org/W6795908048","https://openalex.org/W6796913975","https://openalex.org/W6798071989","https://openalex.org/W6802325372","https://openalex.org/W6803111106","https://openalex.org/W6804171592","https://openalex.org/W6843745752","https://openalex.org/W6853850813","https://openalex.org/W6861974559","https://openalex.org/W7043747221"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","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"],"abstract_inverted_index":{"The":[0,158,181],"prevalent":[1],"utilization":[2],"of":[3,37,96,226,250],"deterministic":[4,167],"strategy":[5,54,168],"algorithms":[6,169],"in":[7,21,58,146,170,192,199,246],"Multi-Agent":[8],"Deep":[9],"Reinforcement":[10],"Learning":[11],"(MADRL)":[12],"for":[13,31],"collaborative":[14],"tasks":[15],"has":[16],"posed":[17],"a":[18,42,51,59,87,149,171,177],"significant":[19],"challenge":[20],"achieving":[22],"stable":[23],"and":[24,35,75,82,123,142,187,216,231],"high-performance":[25],"cooperative":[26,193],"behavior.":[27],"Addressing":[28],"the":[29,32,70,94,97,100,107,112,119,125,129,135,154,221,236,243,248],"need":[30],"balanced":[33],"exploration":[34],"exploitation":[36],"multi-agent":[38,52,147,166,178,194,251],"ant":[39,179,195,252],"robots":[40],"within":[41,255],"partially":[43],"observable":[44],"continuous":[45,172],"action":[46,83],"space,":[47],"this":[48,68],"study":[49],"introduces":[50],"centralized":[53,150],"gradient":[55],"algorithm":[56,71,222],"grounded":[57],"local":[60,73,76,80,103,113,120,130],"state":[61,74,89,109,114,121,131],"transition":[62],"mechanism.":[63],"In":[64],"order":[65],"to":[66,118,127,235],"solve":[67],"challenge,":[69],"learns":[72],"state-action":[77],"representation":[78,105],"from":[79],"observations":[81],"values,":[84],"thereby":[85],"establishing":[86],"\u201clocal":[88],"transition\u201d":[90],"mechanism":[91],"autonomously.":[92],"As":[93],"input":[95,108],"actor":[98],"network,":[99],"automatically":[101],"extracted":[102],"observation":[104,137],"reduces":[106],"dimension,":[110],"enhances":[111],"features":[115,132],"closely":[116],"related":[117],"transition,":[122],"promotes":[124],"agent":[126],"use":[128],"that":[133],"affect":[134],"next":[136],"state.":[138],"To":[139],"mitigate":[140],"non-stationarity":[141],"reliability":[143],"assignment":[144],"issues":[145],"environments,":[148],"critic":[151],"network":[152],"evaluates":[153],"current":[155],"joint":[156],"strategy.":[157],"proposed":[159],"algorithm,":[160],"NST-FACMAC,":[161],"is":[162],"evaluated":[163],"alongside":[164],"other":[165],"control":[173,254],"simulation":[174,196],"environment":[175],"using":[176],"robot.":[180],"experimental":[182],"results":[183],"indicate":[184],"accelerated":[185],"convergence":[186],"higher":[188],"average":[189],"reward":[190],"values":[191],"environments.":[197,257],"Notably,":[198],"four":[200],"simulated":[201],"environments":[202],"named":[203],"Ant-v2":[204,208,212],"(2":[205,209,218],"\u00d7":[206,210,214,219],"4),":[207],"4d),":[211],"(4":[213],"2),":[215],"Manyant":[217],"3),":[220],"demonstrates":[223],"performance":[224],"improvements":[225],"approximately":[227],"1.9%,":[228],"4.8%,":[229],"11.9%,":[230],"36.1%,":[232],"respectively,":[233],"compared":[234],"best":[237],"baseline":[238],"algorithm.":[239],"These":[240],"findings":[241],"underscore":[242],"algorithm\u2019s":[244],"effectiveness":[245],"enhancing":[247],"stability":[249],"robot":[253],"dynamic":[256]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}