{"id":"https://openalex.org/W2898680164","doi":"https://doi.org/10.1109/access.2018.2878853","title":"A Gradient-Based Reinforcement Learning Algorithm for Multiple Cooperative Agents","display_name":"A Gradient-Based Reinforcement Learning Algorithm for Multiple Cooperative Agents","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2898680164","doi":"https://doi.org/10.1109/access.2018.2878853","mag":"2898680164"},"language":"en","primary_location":{"id":"doi:10.1109/access.2018.2878853","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2878853","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2018.2878853","any_repository_has_fulltext":true},"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":false,"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 Automation, Qingdao University, Qingdao, China"],"raw_orcid":null,"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/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042676883","display_name":"Qiaoni Han","orcid":"https://orcid.org/0000-0003-1662-6609"},"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":"Qiaoni Han","raw_affiliation_strings":["School of Automation, Qingdao University, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Qingdao University, Qingdao, China","institution_ids":["https://openalex.org/I108688024"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101852693","display_name":"Tingting Song","orcid":"https://orcid.org/0000-0002-2970-0129"},"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":"Tingting Song","raw_affiliation_strings":["School of Automation, Qingdao University, Qingdao, China"],"raw_orcid":null,"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":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.6758,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78221138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"6","issue":null,"first_page":"70223","last_page":"70235"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9868999719619751,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8210682272911072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.586542010307312},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5127645134925842},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4696499705314636},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.46946823596954346},{"id":"https://openalex.org/keywords/infinitesimal","display_name":"Infinitesimal","score":0.461227685213089},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4412789046764374},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3534652590751648},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3517117202281952},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2454131543636322},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.17432036995887756}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8210682272911072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.586542010307312},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5127645134925842},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4696499705314636},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.46946823596954346},{"id":"https://openalex.org/C91229774","wikidata":"https://www.wikidata.org/wiki/Q193885","display_name":"Infinitesimal","level":2,"score":0.461227685213089},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4412789046764374},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3534652590751648},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3517117202281952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2454131543636322},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.17432036995887756},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2018.2878853","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2878853","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8eaebd97e1574567be7a7f56af0df567","is_oa":true,"landing_page_url":"https://doaj.org/article/8eaebd97e1574567be7a7f56af0df567","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 6, Pp 70223-70235 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2018.2878853","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2878853","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"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/G548514496","display_name":null,"funder_award_id":"ZR2017PF005","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G5528124030","display_name":null,"funder_award_id":"61803218","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5745859652","display_name":null,"funder_award_id":"61573353","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7163010157","display_name":"\u57fa\u4e8e\u6570\u636e\u7684\u5efa\u7b51\u7fa4\u53ca\u5206\u5e03\u5f0f\u80fd\u6e90\u7cfb\u7edf\u4e00\u4f53\u5316\u5efa\u6a21\u4e0e\u81ea\u5b66\u4e60\u4f18\u5316\u63a7\u5236","funder_award_id":"61533017","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":47,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1192553058","https://openalex.org/W1514633502","https://openalex.org/W1519783625","https://openalex.org/W1552825266","https://openalex.org/W1607392272","https://openalex.org/W1970617037","https://openalex.org/W2000029621","https://openalex.org/W2045817941","https://openalex.org/W2046376809","https://openalex.org/W2083535091","https://openalex.org/W2096145798","https://openalex.org/W2099602914","https://openalex.org/W2099618002","https://openalex.org/W2106471678","https://openalex.org/W2108383324","https://openalex.org/W2110906765","https://openalex.org/W2120327309","https://openalex.org/W2120846115","https://openalex.org/W2136934807","https://openalex.org/W2141837602","https://openalex.org/W2148053762","https://openalex.org/W2150758132","https://openalex.org/W2155027007","https://openalex.org/W2158029347","https://openalex.org/W2164637474","https://openalex.org/W2180467047","https://openalex.org/W2183137222","https://openalex.org/W2480536132","https://openalex.org/W2538000344","https://openalex.org/W2568019971","https://openalex.org/W2737995649","https://openalex.org/W2765672669","https://openalex.org/W2802349643","https://openalex.org/W3139377883","https://openalex.org/W6630755865","https://openalex.org/W6631168379","https://openalex.org/W6636288269","https://openalex.org/W6674743605","https://openalex.org/W6676769901","https://openalex.org/W6678168664","https://openalex.org/W6680209877","https://openalex.org/W6683204974","https://openalex.org/W6683289773","https://openalex.org/W6684470913","https://openalex.org/W6792155000","https://openalex.org/W6910535780"],"related_works":["https://openalex.org/W2370598571","https://openalex.org/W2355499472","https://openalex.org/W2349230259","https://openalex.org/W2370818987","https://openalex.org/W2350226651","https://openalex.org/W2361379965","https://openalex.org/W2385204246","https://openalex.org/W2385510272","https://openalex.org/W2348667803","https://openalex.org/W2951274008"],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1],"learning":[2],"(MARL)":[3],"can":[4,118,127],"be":[5,119,128],"used":[6,148],"to":[7,35,84,131],"design":[8],"intelligent":[9],"agents":[10],"for":[11,163],"solving":[12],"cooperative":[13,133],"tasks.":[14],"Within":[15],"the":[16,22,29,37,66,75,81,86,90,114,156],"MARL":[17],"category,":[18],"this":[19],"paper":[20],"proposes":[21],"probability":[23,91],"of":[24,74,92,106,109],"maximal":[25,38,93,115],"reward":[26,40,94,117],"based":[27,95],"on":[28,96],"infinitesimal":[30],"gradient":[31,87,98],"ascent":[32,99],"(PMR-IGA)":[33],"algorithm":[34],"reach":[36],"total":[39,116],"in":[41,48],"repeated":[42,51,110],"games.":[43,135,166],"Theoretical":[44,102],"analyses":[45,103],"show":[46,112,154],"that":[47,113,155],"a":[49,143],"finite-player-finite-action":[50],"game":[52],"with":[53],"two":[54],"pure":[55],"optimal":[56,67],"joint":[57,68],"actions":[58,69],"where":[59],"no":[60],"common":[61],"component":[62],"action":[63],"exists,":[64],"both":[65,164],"are":[70,147],"stable":[71],"critical":[72],"points":[73],"PMR-IGA":[76],"model.":[77],"Furthermore,":[78],"we":[79],"apply":[80],"Q-value":[82],"function":[83],"estimate":[85],"and":[88,104,142],"derive":[89],"estimated":[97],"(PMR-EGA)":[100],"algorithm.":[101],"simulations":[105,153],"case":[107],"studies":[108],"games":[111],"achieved":[120],"under":[121],"any":[122],"initial":[123],"conditions.":[124],"The":[125,152],"PMR-EGA":[126,157],"naturally":[129],"extended":[130],"optimize":[132],"stochastic":[134,137,165],"Two":[136],"games,":[138],"i.e.,":[139],"box":[140],"pushing":[141],"distributed":[144],"sensor":[145],"network,":[146],"as":[149],"test":[150],"beds.":[151],"displays":[158],"consistently":[159],"an":[160],"excellent":[161],"performance":[162]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}