{"id":"https://openalex.org/W3012335515","doi":"https://doi.org/10.1109/cdc40024.2019.9030158","title":"Reinforcement Learning for Decentralized Stochastic Control","display_name":"Reinforcement Learning for Decentralized Stochastic Control","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3012335515","doi":"https://doi.org/10.1109/cdc40024.2019.9030158","mag":"3012335515"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9030158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9030158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://qspace.library.queensu.ca/bitstreams/1579e9ff-1787-4c1f-9d3e-88058c8a7266/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017866507","display_name":"Bora Yongacoglu","orcid":null},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bora Yongacoglu","raw_affiliation_strings":["Department of Mathematics and Statistics, Queen\u2019s University, Kingston, ON, Canada","Department of Mathematics and Statistics, Queen's University, Kingston, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen\u2019s University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072860374","display_name":"G\u00fcrdal Arslan","orcid":"https://orcid.org/0000-0002-8295-1509"},"institutions":[{"id":"https://openalex.org/I1331384533","display_name":"University of Hawaii System","ror":"https://ror.org/03tzaeb71","country_code":"US","type":"education","lineage":["https://openalex.org/I1331384533"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gurdal Arslan","raw_affiliation_strings":["University of Hawaii"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hawaii","institution_ids":["https://openalex.org/I1331384533"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005401257","display_name":"Serdar Y\u00fcksel","orcid":"https://orcid.org/0000-0001-6099-5001"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Serdar Yuksel","raw_affiliation_strings":["Department of Mathematics and Statistics, Queen\u2019s University, Kingston, ON, Canada","Department of Mathematics and Statistics, Queen's University, Kingston, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen\u2019s University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8676,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81896704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5556","last_page":"5561"},"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/T11031","display_name":"Game Theory and Applications","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8426936864852905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6995631456375122},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4896736443042755},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.48634201288223267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41824087500572205},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13563048839569092}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8426936864852905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995631456375122},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4896736443042755},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.48634201288223267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41824087500572205},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13563048839569092},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc40024.2019.9030158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9030158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:qspace.library.queensu.ca:1974/24481","is_oa":true,"landing_page_url":"http://hdl.handle.net/1974/24481","pdf_url":"http://qspace.library.queensu.ca/bitstreams/1579e9ff-1787-4c1f-9d3e-88058c8a7266/download","source":{"id":"https://openalex.org/S4306402568","display_name":"QSpace (Queen's University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I204722609","host_organization_name":"Queen's University","host_organization_lineage":["https://openalex.org/I204722609"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"thesis"}],"best_oa_location":{"id":"pmh:oai:qspace.library.queensu.ca:1974/24481","is_oa":true,"landing_page_url":"http://hdl.handle.net/1974/24481","pdf_url":"http://qspace.library.queensu.ca/bitstreams/1579e9ff-1787-4c1f-9d3e-88058c8a7266/download","source":{"id":"https://openalex.org/S4306402568","display_name":"QSpace (Queen's University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I204722609","host_organization_name":"Queen's University","host_organization_lineage":["https://openalex.org/I204722609"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"thesis"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3012335515.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W585548487","https://openalex.org/W1513468570","https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W1641379095","https://openalex.org/W1964886424","https://openalex.org/W2005228957","https://openalex.org/W2010654234","https://openalex.org/W2064882565","https://openalex.org/W2067018002","https://openalex.org/W2104602264","https://openalex.org/W2118994458","https://openalex.org/W2120846115","https://openalex.org/W2121863487","https://openalex.org/W2142839172","https://openalex.org/W2145067550","https://openalex.org/W2147750403","https://openalex.org/W2150339816","https://openalex.org/W2156194062","https://openalex.org/W2176451521","https://openalex.org/W2337001255","https://openalex.org/W2570514057","https://openalex.org/W2788115019","https://openalex.org/W2962990479","https://openalex.org/W2972782056","https://openalex.org/W3011120880","https://openalex.org/W3102463202","https://openalex.org/W4230410498","https://openalex.org/W4233696721","https://openalex.org/W6630520071","https://openalex.org/W6631168379","https://openalex.org/W6675811377","https://openalex.org/W6678168664","https://openalex.org/W6681246212","https://openalex.org/W6681342480","https://openalex.org/W6749032143","https://openalex.org/W6767800324","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2089013912","https://openalex.org/W2107890255","https://openalex.org/W2076061571","https://openalex.org/W2106552856","https://openalex.org/W1987513656"],"abstract_inverted_index":{"In":[0,65,116],"the":[1,24,28],"study":[2],"of":[3,20,23],"stochastic":[4,81,86,94],"dynamic":[5,82,95],"team":[6,112],"problems,":[7],"analytical":[8],"methods":[9,43],"for":[10,44,74,132],"finding":[11,75],"optimal":[12,63,113,136],"policies":[13,77,103],"are":[14,142],"often":[15],"inapplicable":[16],"due":[17],"to":[18,37,62,134,151],"lack":[19],"prior":[21],"knowledge":[22],"cost":[25,105,156],"function":[26],"or":[27,54],"state":[29,162],"dynamics.":[30],"Reinforcement":[31],"learning":[32,42,123],"offers":[33],"a":[34,66,71,111,121],"possible":[35],"solution":[36],"such":[38,154],"coordination":[39],"problems.":[40],"Existing":[41],"coordinating":[45],"play":[46],"either":[47],"rely":[48],"on":[49],"control":[50],"sharing":[51],"among":[52],"controllers":[53],"otherwise,":[55],"in":[56,78,98,145],"general,":[57],"do":[58],"not":[59],"guarantee":[60],"convergence":[61,133],"policies.":[64,137],"recent":[67],"paper,":[68,118],"we":[69,119],"provided":[70],"decentralized":[72,144],"algorithm":[73,124],"equilibrium":[76,102],"weakly":[79],"acyclic":[80],"games,":[83],"which":[84],"contain":[85],"teams":[87,96],"as":[88,155],"an":[89],"important":[90],"special":[91],"case.":[92],"However,":[93],"can":[97,106],"general":[99],"possess":[100],"suboptimal":[101],"whose":[104],"be":[107],"arbitrarily":[108],"higher":[109],"than":[110],"policy's":[114],"cost.":[115],"this":[117],"present":[120],"reinforcement":[122],"and":[125,128,161],"its":[126],"refinements,":[127],"provide":[129],"probabilistic":[130],"guarantees":[131],"globally":[135],"The":[138],"algorithms":[139],"presented":[140],"here":[141],"strictly":[143],"that":[146],"they":[147],"require":[148],"only":[149],"access":[150],"local":[152,159],"information":[153],"realizations,":[157],"previous":[158],"actions,":[160],"transitions.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}