{"id":"https://openalex.org/W4408399536","doi":"https://doi.org/10.1109/tcsi.2025.3548900","title":"Reinforcement Learning Solutions to Stochastic Multi-Agent Graphical Games With Multiplicative Noise","display_name":"Reinforcement Learning Solutions to Stochastic Multi-Agent Graphical Games With Multiplicative Noise","publication_year":2025,"publication_date":"2025-03-13","ids":{"openalex":"https://openalex.org/W4408399536","doi":"https://doi.org/10.1109/tcsi.2025.3548900"},"language":"en","primary_location":{"id":"doi:10.1109/tcsi.2025.3548900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2025.3548900","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"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 Circuits and Systems I: Regular Papers","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":null,"display_name":"Hanfang Zhang","orcid":"https://orcid.org/0009-0006-7499-8485"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hanfang Zhang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0006-7499-8485","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017397385","display_name":"Bing\u2010Chang Wang","orcid":"https://orcid.org/0000-0003-3882-8615"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Chang Wang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-3882-8615","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084256265","display_name":"Ying Cao","orcid":"https://orcid.org/0000-0003-4392-5866"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Cao","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":5.6199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94687305,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"72","issue":"7","first_page":"3570","last_page":"3583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12137","display_name":"Economic theories and models","score":0.620199978351593,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12137","display_name":"Economic theories and models","score":0.620199978351593,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.5464000105857849,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7757962942123413},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6083852648735046},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5758456587791443},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5748118162155151},{"id":"https://openalex.org/keywords/multiplicative-noise","display_name":"Multiplicative noise","score":0.512005627155304},{"id":"https://openalex.org/keywords/multiplicative-function","display_name":"Multiplicative function","score":0.49603065848350525},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.337942898273468},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3086473345756531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30824556946754456},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14366161823272705},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14188259840011597},{"id":"https://openalex.org/keywords/transmission","display_name":"Transmission (telecommunications)","score":0.12089303135871887},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.10480833053588867}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7757962942123413},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6083852648735046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5758456587791443},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5748118162155151},{"id":"https://openalex.org/C18015164","wikidata":"https://www.wikidata.org/wiki/Q6935000","display_name":"Multiplicative noise","level":5,"score":0.512005627155304},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.49603065848350525},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.337942898273468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3086473345756531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30824556946754456},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14366161823272705},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14188259840011597},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.12089303135871887},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.10480833053588867},{"id":"https://openalex.org/C13412647","wikidata":"https://www.wikidata.org/wiki/Q174948","display_name":"Analog signal","level":3,"score":0.0},{"id":"https://openalex.org/C131021393","wikidata":"https://www.wikidata.org/wiki/Q7512759","display_name":"Signal transfer function","level":4,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsi.2025.3548900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2025.3548900","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"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 Circuits and Systems I: Regular Papers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3521150767","display_name":null,"funder_award_id":"62122043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4553523842","display_name":null,"funder_award_id":"62192753","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G872276605","display_name":null,"funder_award_id":"ZR2022JQ31","funder_id":"https://openalex.org/F4320336607","funder_display_name":"Natural Science Foundation of Guangdong Province for Distinguished Young Scholars"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336607","display_name":"Natural Science Foundation of Guangdong Province for Distinguished Young Scholars","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2025421018","https://openalex.org/W2045719273","https://openalex.org/W2086977346","https://openalex.org/W2094034361","https://openalex.org/W2099175737","https://openalex.org/W2108286682","https://openalex.org/W2113127719","https://openalex.org/W2131363581","https://openalex.org/W2132858840","https://openalex.org/W2137092694","https://openalex.org/W2165744313","https://openalex.org/W2484646121","https://openalex.org/W2602009922","https://openalex.org/W2621714194","https://openalex.org/W2768195099","https://openalex.org/W2791370321","https://openalex.org/W2905422675","https://openalex.org/W3033183381","https://openalex.org/W3128521811","https://openalex.org/W3137906938","https://openalex.org/W3180881483","https://openalex.org/W4205501012","https://openalex.org/W4210989438","https://openalex.org/W4212780424","https://openalex.org/W4252284432","https://openalex.org/W4293047668","https://openalex.org/W4308902993","https://openalex.org/W4364322321","https://openalex.org/W4381162568","https://openalex.org/W4383684904","https://openalex.org/W4385552642","https://openalex.org/W4386095954","https://openalex.org/W4386744270","https://openalex.org/W4388977050","https://openalex.org/W4390532794","https://openalex.org/W4390660393","https://openalex.org/W4391147753","https://openalex.org/W4392515548","https://openalex.org/W4393942688","https://openalex.org/W4399770676","https://openalex.org/W4401866408","https://openalex.org/W6730724551","https://openalex.org/W6802973543"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W4287812451","https://openalex.org/W3022718941","https://openalex.org/W2150219835","https://openalex.org/W1996414039","https://openalex.org/W2506602630","https://openalex.org/W3097284316"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"reinforcement":[3],"learning":[4],"algorithms":[5],"for":[6,19],"discrete-time":[7],"stochastic":[8,20],"multi-agent":[9,21,76],"graphical":[10,22,77],"games":[11,23,78],"with":[12],"multiplicative":[13],"noise.":[14],"The":[15,95],"Bellman":[16,46,57],"optimality":[17,29,47],"equation":[18],"is":[24,67,72,88,100],"obtained":[25],"by":[26,102],"using":[27],"the":[28,51,55,80,85,98],"principle.":[30],"A":[31],"Nash":[32,92],"equilibrium":[33,93],"can":[34],"be":[35],"reached":[36],"when":[37],"each":[38],"agent":[39],"executes":[40],"a":[41,59],"strategy":[42],"in":[43],"terms":[44],"of":[45,53,97],"equation.":[48],"To":[49,74],"circumvent":[50],"difficulty":[52],"solving":[54],"coupled":[56],"equation,":[58],"value":[60],"iteration":[61],"heuristic":[62],"dynamic":[63],"programming":[64],"(HDP)":[65],"algorithm":[66,82,99],"designed":[68,89],"and":[69],"its":[70],"convergence":[71],"shown.":[73],"solve":[75],"online,":[79],"HDP":[81],"based":[83],"on":[84],"actor-critic":[86],"framework":[87],"to":[90],"approximate":[91],"solutions.":[94],"effectiveness":[96],"verified":[101],"two":[103],"numerical":[104],"simulation":[105],"examples.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}