{"id":"https://openalex.org/W3012925600","doi":"https://doi.org/10.1109/ciss50987.2021.9400275","title":"Decentralized Multi-agent Reinforcement Learning with Shared Actions","display_name":"Decentralized Multi-agent Reinforcement Learning with Shared Actions","publication_year":2021,"publication_date":"2021-03-24","ids":{"openalex":"https://openalex.org/W3012925600","doi":"https://doi.org/10.1109/ciss50987.2021.9400275","mag":"3012925600"},"language":"en","primary_location":{"id":"doi:10.1109/ciss50987.2021.9400275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss50987.2021.9400275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 55th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.10185","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101638971","display_name":"Rajesh Mishra","orcid":"https://orcid.org/0009-0005-4410-1940"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajesh K Mishra","raw_affiliation_strings":["University of Texas, Austin, TX","University of Texas,Department of ECE,Austin,TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas, Austin, TX","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas,Department of ECE,Austin,TX","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045766079","display_name":"Deepanshu Vasal","orcid":"https://orcid.org/0000-0003-1089-8080"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deepanshu Vasal","raw_affiliation_strings":["Northwestern University, Evanston, IL","Northwestern University,Department of ECE,Evanston,IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, IL","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern University,Department of ECE,Evanston,IL","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088120102","display_name":"Sriram Vishwanath","orcid":"https://orcid.org/0000-0003-3112-4885"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Vishwanath","raw_affiliation_strings":["University of Texas, Austin, TX","University of Texas,Department of ECE,Austin,TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas, Austin, TX","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas,Department of ECE,Austin,TX","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1468,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32239697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9983999729156494,"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":0.9980000257492065,"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":0.8727791905403137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7092471122741699},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.6026394963264465},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5740694999694824},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4818505048751831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4753187298774719},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.47267991304397583},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4469335973262787},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4407033920288086},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4265858829021454},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4131772220134735},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3511433005332947},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2520342469215393},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1199454665184021},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11248376965522766},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.09386253356933594}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8727791905403137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092471122741699},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.6026394963264465},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5740694999694824},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4818505048751831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4753187298774719},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.47267991304397583},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4469335973262787},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4407033920288086},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4265858829021454},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4131772220134735},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3511433005332947},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2520342469215393},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1199454665184021},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11248376965522766},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.09386253356933594},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ciss50987.2021.9400275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss50987.2021.9400275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 55th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2003.10185","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.10185","pdf_url":"https://arxiv.org/pdf/2003.10185","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2003.10185","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.10185","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3012925600","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.10185","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.10185","pdf_url":"https://arxiv.org/pdf/2003.10185","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3012925600.pdf","grobid_xml":"https://content.openalex.org/works/W3012925600.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1488636191","https://openalex.org/W1683981004","https://openalex.org/W1982576580","https://openalex.org/W1991888757","https://openalex.org/W2063844956","https://openalex.org/W2077611006","https://openalex.org/W2103012681","https://openalex.org/W2105876604","https://openalex.org/W2120545133","https://openalex.org/W2130363011","https://openalex.org/W2130985368","https://openalex.org/W2146890818","https://openalex.org/W2162733643","https://openalex.org/W2165377048","https://openalex.org/W2341285855","https://openalex.org/W2604873668","https://openalex.org/W2947846187","https://openalex.org/W2963747324","https://openalex.org/W3004213034","https://openalex.org/W3011813374","https://openalex.org/W3101156441","https://openalex.org/W6677763144","https://openalex.org/W6679627699","https://openalex.org/W6746015766","https://openalex.org/W6749032143"],"related_works":["https://openalex.org/W3207697547","https://openalex.org/W103885025","https://openalex.org/W1496168875","https://openalex.org/W2057760454","https://openalex.org/W3165228974","https://openalex.org/W2952222762","https://openalex.org/W3201487093","https://openalex.org/W65230124","https://openalex.org/W3132127507","https://openalex.org/W3093356339","https://openalex.org/W2920567230","https://openalex.org/W2376619035","https://openalex.org/W2895808298","https://openalex.org/W2750605955","https://openalex.org/W2901992463","https://openalex.org/W2912250739","https://openalex.org/W1984728996","https://openalex.org/W1528484975","https://openalex.org/W3101554308","https://openalex.org/W2972387988"],"abstract_inverted_index":{"In":[0,111],"this":[1,112],"paper,":[2,113],"we":[3,114,162],"consider":[4],"a":[5,29,80,130,141],"multi-agent":[6],"system":[7,109],"with":[8,59,137],"N":[9],"cooperative":[10],"agents":[11,42,128,157],"where":[12,144],"each":[13,24,95],"agent":[14,66,73,96],"privately":[15],"observes":[16,23],"its":[17],"own":[18],"private":[19],"type":[20],"and":[21,101,168],"publicly":[22],"others'":[25],"actions.":[26],"We":[27,62,133],"propose":[28],"novel":[30],"model-free":[31,169],"reinforcement":[32,173],"learning":[33,174],"algorithm":[34,176],"to":[35,51,122,148],"compute":[36],"the":[37,41,52,64,75,83,87,105,108,119,124,138,145,156,159,164,172,178],"optimal":[38],"policies":[39],"for":[40,94,154,166],"that":[43],"maximizes":[44],"their":[45,98],"collective":[46,150],"reward.":[47],"This":[48],"setting":[49],"belongs":[50],"broad":[53],"class":[54],"of":[55,86,107,126,140,152,171,180],"decentralized":[56],"control":[57],"problems":[58],"partial":[60],"information.":[61],"use":[63],"common":[65,72],"approach":[67],"[1],":[68],"wherein":[69],"some":[70],"fictitious":[71],"chooses":[74],"best":[76],"policy":[77],"based":[78],"on":[79,82],"belief":[81,100,125],"current":[84,99],"states":[85],"agents.":[88],"These":[89],"beliefs":[90],"are":[91],"updated":[92],"individually":[93],"from":[97],"action":[102],"histories":[103],"without":[104],"knowledge":[106],"dynamics.":[110],"employ":[115],"particle":[116,181],"filters,":[117,121],"called":[118],"bootstrap":[120],"update":[123],"all":[127,155],"in":[129,158],"distributed":[131],"manner.":[132],"illustrate":[134],"our":[135],"results":[136],"help":[139],"smart-grid":[142],"application,":[143],"users":[146],"strive":[147],"reduce":[149],"cost":[151],"power":[153],"grid.":[160],"Finally,":[161],"compare":[163],"performances":[165],"model":[167],"implementation":[170],"(RL)":[175],"establishing":[177],"effectiveness":[179],"filter":[182],"(PF)":[183],"method.":[184]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}