{"id":"https://openalex.org/W4221146329","doi":"https://doi.org/10.23919/acc53348.2022.9867152","title":"Distributed Cooperative Multi-Agent Reinforcement Learning with Directed Coordination Graph","display_name":"Distributed Cooperative Multi-Agent Reinforcement Learning with Directed Coordination Graph","publication_year":2022,"publication_date":"2022-06-08","ids":{"openalex":"https://openalex.org/W4221146329","doi":"https://doi.org/10.23919/acc53348.2022.9867152"},"language":"en","primary_location":{"id":"doi:10.23919/acc53348.2022.9867152","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867152","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 American Control Conference (ACC)","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/A5073846906","display_name":"Gangshan Jing","orcid":"https://orcid.org/0000-0003-0066-204X"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gangshan Jing","raw_affiliation_strings":["Chongqing University,School of Automation,Chongqing,China,400044"],"affiliations":[{"raw_affiliation_string":"Chongqing University,School of Automation,Chongqing,China,400044","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040513070","display_name":"He Bai","orcid":"https://orcid.org/0000-0002-4247-0698"},"institutions":[{"id":"https://openalex.org/I115475287","display_name":"Oklahoma State University","ror":"https://ror.org/01g9vbr38","country_code":"US","type":"education","lineage":["https://openalex.org/I115475287"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He Bai","raw_affiliation_strings":["Oklahoma State University,Stillwater,OK,USA,74078"],"affiliations":[{"raw_affiliation_string":"Oklahoma State University,Stillwater,OK,USA,74078","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054187846","display_name":"Jemin George","orcid":"https://orcid.org/0000-0001-8417-5411"},"institutions":[{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jemin George","raw_affiliation_strings":["DEVCOM U.S. Army Research Laboratory,Adelphi,MD,USA,20783"],"affiliations":[{"raw_affiliation_string":"DEVCOM U.S. Army Research Laboratory,Adelphi,MD,USA,20783","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055360778","display_name":"Aranya Chakrabortty","orcid":"https://orcid.org/0000-0002-3474-8215"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aranya Chakrabortty","raw_affiliation_strings":["North Carolina State University,Raleigh,NC,USA,27695"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Raleigh,NC,USA,27695","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100679053","display_name":"Piyush Sharma","orcid":"https://orcid.org/0000-0002-6953-3652"},"institutions":[{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piyush. K. Sharma","raw_affiliation_strings":["DEVCOM U.S. Army Research Laboratory,Adelphi,MD,USA,20783"],"affiliations":[{"raw_affiliation_string":"DEVCOM U.S. Army Research Laboratory,Adelphi,MD,USA,20783","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073846906"],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":0.5197,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60978237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3273","last_page":"3278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9983000159263611,"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":0.9965999722480774,"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":0.8534625768661499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7646905183792114},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7366513609886169},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.532565176486969},{"id":"https://openalex.org/keywords/distributed-algorithm","display_name":"Distributed algorithm","score":0.5134597420692444},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4577582776546478},{"id":"https://openalex.org/keywords/directed-graph","display_name":"Directed graph","score":0.43967241048812866},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.4218592941761017},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3467486500740051},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3216992914676666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23428156971931458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22082334756851196},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10262587666511536}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8534625768661499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646905183792114},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7366513609886169},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.532565176486969},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.5134597420692444},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4577582776546478},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.43967241048812866},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.4218592941761017},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3467486500740051},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3216992914676666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23428156971931458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22082334756851196},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10262587666511536},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc53348.2022.9867152","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867152","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1918371733","https://openalex.org/W2110906765","https://openalex.org/W2118318536","https://openalex.org/W2149479912","https://openalex.org/W2788115019","https://openalex.org/W2993990522","https://openalex.org/W3027121709","https://openalex.org/W3036086835","https://openalex.org/W3036279995","https://openalex.org/W3156295478","https://openalex.org/W3163894240","https://openalex.org/W4221146329","https://openalex.org/W4287758272","https://openalex.org/W4288614813","https://openalex.org/W6676769901","https://openalex.org/W6677834374","https://openalex.org/W6749032143","https://openalex.org/W6758646351","https://openalex.org/W6771232374","https://openalex.org/W6779257429","https://openalex.org/W6779874797","https://openalex.org/W6780308666","https://openalex.org/W6794146056","https://openalex.org/W6794679647"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2389214306","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2166734474"],"abstract_inverted_index":{"Existing":[0],"distributed":[1,58,125,132],"cooperative":[2],"multi-agent":[3],"reinforcement":[4],"learning":[5],"(MARL)":[6],"frameworks":[7],"usually":[8],"assume":[9],"undirected":[10],"coordination":[11,53],"graphs":[12],"and":[13,35,55],"communication":[14,33,83,91],"graphs,":[15,54],"while":[16],"estimating":[17],"a":[18,28,57,88],"global":[19,43],"reward":[20],"via":[21],"consensus":[22,96],"algorithms":[23],"for":[24],"policy":[25,64],"evaluation.":[26],"Such":[27],"framework":[29],"may":[30],"induce":[31],"expensive":[32],"costs":[34],"exhibit":[36],"poor":[37],"scalability":[38],"due":[39],"to":[40,109,138],"requirement":[41],"of":[42,76,142],"consensus.":[44],"In":[45],"this":[46],"work,":[47],"we":[48,120],"study":[49],"MARLs":[50],"with":[51,84,115],"directed":[52,89],"propose":[56],"RL":[59,118,126],"algorithm":[60,127],"where":[61],"the":[62,140],"local":[63,69,73,82],"evaluations":[65],"are":[66],"based":[67,103],"on":[68,104],"value":[70,74],"functions.":[71],"The":[72],"function":[75],"each":[77],"agent":[78],"is":[79,107,136],"obtained":[80],"by":[81],"its":[85],"neighbors":[86],"through":[87],"learning-induced":[90],"graph,":[92],"without":[93],"using":[94],"any":[95],"algorithm.":[97,144],"A":[98,131],"zeroth-order":[99],"optimization":[100],"(ZOO)":[101],"approach":[102],"parameter":[105],"perturbation":[106],"employed":[108],"achieve":[110],"gradient":[111],"estimation.":[112],"By":[113],"comparing":[114],"existing":[116],"ZOO-based":[117],"algorithms,":[119],"show":[121],"that":[122],"our":[123,143],"proposed":[124],"guarantees":[128],"high":[129],"scalability.":[130],"resource":[133],"allocation":[134],"example":[135],"shown":[137],"illustrate":[139],"effectiveness":[141]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
