{"id":"https://openalex.org/W2613194908","doi":"https://doi.org/10.1109/tac.2017.2702203","title":"Centralized Optimization for Dec-POMDPs Under the Expected Average Reward Criterion","display_name":"Centralized Optimization for Dec-POMDPs Under the Expected Average Reward Criterion","publication_year":2017,"publication_date":"2017-05-12","ids":{"openalex":"https://openalex.org/W2613194908","doi":"https://doi.org/10.1109/tac.2017.2702203","mag":"2613194908"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2017.2702203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2017.2702203","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","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":"https://openalex.org/A5088416755","display_name":"Xiaofeng Jiang","orcid":"https://orcid.org/0000-0001-7595-2397"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Xiaofeng Jiang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China","Department of Electrical Engineering, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382658","display_name":"Xiaodong Wang","orcid":"https://orcid.org/0000-0002-2945-9240"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069802328","display_name":"Hongsheng Xi","orcid":"https://orcid.org/0000-0002-5747-9732"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongsheng Xi","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046052004","display_name":"Falin Liu","orcid":"https://orcid.org/0000-0001-6815-7133"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Falin Liu","raw_affiliation_strings":["Department of Electric Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Electric Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088416755"],"corresponding_institution_ids":["https://openalex.org/I126520041","https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":0.39,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6903536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"62","issue":"11","first_page":"6032","last_page":"6038"},"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9901999831199646,"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9883000254631042,"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.9334072470664978},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7474091649055481},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6847813129425049},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6829496622085571},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.5534883141517639},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.45818769931793213},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44080162048339844},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4355151057243347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2781330943107605},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25020503997802734},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15385037660598755},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.08268579840660095}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.9334072470664978},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7474091649055481},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6847813129425049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6829496622085571},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5534883141517639},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.45818769931793213},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44080162048339844},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4355151057243347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2781330943107605},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25020503997802734},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15385037660598755},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.08268579840660095},{"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":1,"locations":[{"id":"doi:10.1109/tac.2017.2702203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2017.2702203","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5156508193","display_name":null,"funder_award_id":"61503358","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6392292501","display_name":null,"funder_award_id":"61233003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8611069936","display_name":null,"funder_award_id":"2014M561839","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W190675879","https://openalex.org/W855114052","https://openalex.org/W1516903196","https://openalex.org/W1555477527","https://openalex.org/W1601795611","https://openalex.org/W1663973292","https://openalex.org/W1908253641","https://openalex.org/W1955857676","https://openalex.org/W1976195538","https://openalex.org/W1991888757","https://openalex.org/W1994616650","https://openalex.org/W2006854168","https://openalex.org/W2034725503","https://openalex.org/W2047663898","https://openalex.org/W2055418958","https://openalex.org/W2080920551","https://openalex.org/W2099430963","https://openalex.org/W2102162493","https://openalex.org/W2119567691","https://openalex.org/W2142819538","https://openalex.org/W2149551746","https://openalex.org/W2156676156","https://openalex.org/W2334782222","https://openalex.org/W2484957131","https://openalex.org/W2611866857","https://openalex.org/W4229543188","https://openalex.org/W4231746564","https://openalex.org/W6607768588","https://openalex.org/W6630841318","https://openalex.org/W6633295396","https://openalex.org/W6640044251"],"related_works":["https://openalex.org/W1760611253","https://openalex.org/W2146763310","https://openalex.org/W131709709","https://openalex.org/W2219400200","https://openalex.org/W2051230701","https://openalex.org/W2009810843","https://openalex.org/W94274217","https://openalex.org/W1568770747","https://openalex.org/W2404525779","https://openalex.org/W2064442004"],"abstract_inverted_index":{"In":[0,76],"this":[1,82],"paper,":[2],"the":[3,40,46,50,63,69,79,87,101,106,109,124,128,162,165],"decentralized":[4,47,88],"partially":[5,41],"observable":[6,42],"Markov":[7],"decision":[8,37,64],"process":[9],"(Dec-POMDP)":[10],"systems":[11],"with":[12],"discrete":[13],"state":[14,71],"and":[15,97,146],"action":[16],"spaces":[17],"are":[18],"studied":[19],"from":[20,133],"a":[21,31,55,115,134],"gradient":[22,107,118,131],"point":[23],"of":[24,49,57,108,130,164],"view.":[25],"Dec-POMDPs":[26],"have":[27,100,113],"recently":[28],"emerged":[29],"as":[30],"promising":[32],"approach":[33],"to":[34,67,78,94,122,150,160],"optimizing":[35,86],"multiagent":[36],"making":[38],"in":[39,54],"stochastic":[43,117],"environment.":[44],"However,":[45],"nature":[48],"Dec-POMDP":[51,153],"framework":[52],"results":[53],"lack":[56],"shared":[58],"belief":[59],"state,":[60],"which":[61,91],"makes":[62],"maker":[65],"impossible":[66],"estimate":[68],"system":[70],"based":[72],"on":[73,85,127],"local":[74],"information.":[75],"contrast":[77],"belief-based":[80],"policy,":[81,90],"paper":[83],"focuses":[84],"observation-based":[89],"is":[92,158],"easily":[93],"be":[95,148],"applied":[96,149],"does":[98,140],"not":[99,141],"sharing":[102],"problem.":[103],"By":[104],"analyzing":[105],"objective":[110],"function,":[111],"we":[112],"developed":[114],"centralized":[116],"policy":[119,126],"iteration":[120],"algorithm":[121,139],"find":[123],"optimal":[125],"basis":[129],"estimates":[132],"single":[135],"sample":[136],"path.":[137],"This":[138],"need":[142],"any":[143],"specific":[144],"assumption":[145],"can":[147],"most":[151],"practical":[152],"problems.":[154],"One":[155],"numerical":[156],"example":[157],"provided":[159],"demonstrate":[161],"effectiveness":[163],"algorithm.":[166]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}