{"id":"https://openalex.org/W3090693621","doi":"https://doi.org/10.1109/ccta41146.2020.9206397","title":"Reinforcement Learning in Deep Structured Teams: Initial Results with Finite and Infinite Valued Features","display_name":"Reinforcement Learning in Deep Structured Teams: Initial Results with Finite and Infinite Valued Features","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3090693621","doi":"https://doi.org/10.1109/ccta41146.2020.9206397","mag":"3090693621"},"language":"en","primary_location":{"id":"doi:10.1109/ccta41146.2020.9206397","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccta41146.2020.9206397","pdf_url":null,"source":{"id":"https://openalex.org/S4306498667","display_name":"2020 IEEE Conference on Control Technology and Applications (CCTA)","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":"2020 IEEE Conference on Control Technology and Applications (CCTA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.02868","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jalal Arabneydi","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Jalal Arabneydi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Concordia University, 1455 de Maisonneuve Blvd. West, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Concordia University, 1455 de Maisonneuve Blvd. West, Montreal, QC, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Masoud Roudneshin","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Masoud Roudneshin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Concordia University, 1455 de Maisonneuve Blvd. West, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Concordia University, 1455 de Maisonneuve Blvd. West, Montreal, QC, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":null,"display_name":"Amir G. Aghdam","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amir G. Aghdam","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Concordia University, 1455 de Maisonneuve Blvd. West, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Concordia University, 1455 de Maisonneuve Blvd. West, Montreal, QC, Canada","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60158472"],"apc_list":null,"apc_paid":null,"fwci":0.4468,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66211309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"148","last_page":"155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8270999789237976,"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":0.8270999789237976,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.023600000888109207,"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"}},{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.010300000198185444,"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/markov-chain","display_name":"Markov chain","score":0.6085000038146973},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4860999882221222},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.4625000059604645},{"id":"https://openalex.org/keywords/linear-model","display_name":"Linear model","score":0.4465999901294708},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.44269999861717224},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.4205999970436096},{"id":"https://openalex.org/keywords/orthonormal-basis","display_name":"Orthonormal basis","score":0.40779998898506165},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.40139999985694885},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3961000144481659}],"concepts":[{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6085000038146973},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5138999819755554},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4860999882221222},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48350000381469727},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.4625000059604645},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C5806529","wikidata":"https://www.wikidata.org/wiki/Q2365325","display_name":"Orthonormal basis","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.38609999418258667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.383899986743927},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3716999888420105},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.37130001187324524},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C189973286","wikidata":"https://www.wikidata.org/wiki/Q176695","display_name":"Markov property","level":4,"score":0.310699999332428},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3066999912261963},{"id":"https://openalex.org/C162392398","wikidata":"https://www.wikidata.org/wiki/Q272404","display_name":"Finite set","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.2896000146865845},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ccta41146.2020.9206397","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccta41146.2020.9206397","pdf_url":null,"source":{"id":"https://openalex.org/S4306498667","display_name":"2020 IEEE Conference on Control Technology and Applications (CCTA)","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":"2020 IEEE Conference on Control Technology and Applications (CCTA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.02868","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.02868","pdf_url":"https://arxiv.org/pdf/2010.02868","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.02868","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.02868","pdf_url":"https://arxiv.org/pdf/2010.02868","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W574171861","https://openalex.org/W2008668719","https://openalex.org/W2069525910","https://openalex.org/W2081287319","https://openalex.org/W2088956500","https://openalex.org/W2955520961","https://openalex.org/W2993887252","https://openalex.org/W4233696721","https://openalex.org/W6801322280"],"related_works":[],"abstract_inverted_index":{"In":[0,33,62],"this":[1,63],"paper,":[2],"we":[3,65],"consider":[4,66],"Markov":[5,72,135],"chain":[6,73,136],"and":[7,17,30,42,80,108,138],"linear":[8,57,69,84,87,141],"quadratic":[9,88,142],"models":[10,74,89,137],"for":[11,71,86,100,115,134,140],"deep":[12,27,34,46,49],"structured":[13,35],"teams":[14],"with":[15],"discounted":[16],"time-average":[18],"cost":[19,43],"functions":[20,44],"under":[21],"two":[22,128],"non-classical":[23],"information":[24],"structures,":[25],"namely,":[26],"state":[28,50],"sharing":[29],"no":[31],"sharing.":[32],"teams,":[36],"agents":[37],"are":[38,98,113,148],"coupled":[39],"in":[40],"dynamics":[41],"through":[45],"state,":[47],"where":[48],"refers":[51],"to":[52,151],"a":[53,67,81,152],"set":[54],"of":[55,59,78,93,127],"orthogonal":[56],"regressions":[58,85],"the":[60,101,104,116,119],"states.":[61],"article,":[64],"homogeneous":[68],"regression":[70],"(i.e.,":[75,90],"empirical":[76],"distribution":[77],"states)":[79],"few":[82],"orthonormal":[83],"weighted":[91],"average":[92],"states).":[94],"Some":[95],"planning":[96],"algorithms":[97,112],"developed":[99],"case":[102,117],"when":[103,118],"model":[105,120],"is":[106,121,144],"known,":[107],"some":[109],"reinforcement":[110],"learning":[111],"proposed":[114],"not":[122],"known":[123],"completely.":[124],"The":[125,146],"convergence":[126],"model-free":[129],"(reinforcement":[130],"learning)":[131],"algorithms,":[132],"one":[133,139],"models,":[143],"established.":[145],"results":[147],"then":[149],"applied":[150],"smart":[153],"grid.":[154]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-10-08T00:00:00"}