{"id":"https://openalex.org/W3023368031","doi":"https://doi.org/10.1109/msp.2020.2976000","title":"Optimization for Reinforcement Learning: From a single agent to cooperative agents","display_name":"Optimization for Reinforcement Learning: From a single agent to cooperative agents","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3023368031","doi":"https://doi.org/10.1109/msp.2020.2976000","mag":"3023368031"},"language":"en","primary_location":{"id":"doi:10.1109/msp.2020.2976000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2020.2976000","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"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 Signal Processing Magazine","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1912.00498","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Donghwan Lee","orcid":"https://orcid.org/0000-0002-4962-8478"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donghwan Lee","raw_affiliation_strings":["Electrical and Computer Engineering, Purdue University, West Lafayette, Indiana"],"raw_orcid":"https://orcid.org/0000-0002-4962-8478","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Purdue University, West Lafayette, Indiana","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Niao He","orcid":"https://orcid.org/0000-0003-4225-7536"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niao He","raw_affiliation_strings":["Department of Industrial and Enterprise Systems Engineering and Coordinated Science Laboratory, University of Illinois at Urbana\u2013Champaign"],"raw_orcid":"https://orcid.org/0000-0003-4225-7536","affiliations":[{"raw_affiliation_string":"Department of Industrial and Enterprise Systems Engineering and Coordinated Science Laboratory, University of Illinois at Urbana\u2013Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Parameswaran Kamalaruban","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Parameswaran Kamalaruban","raw_affiliation_strings":["Postdoctoral Researcher, Ecole Polytechnique f\u00e9d\u00e9rale de Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Postdoctoral Researcher, Ecole Polytechnique f\u00e9d\u00e9rale de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":null,"display_name":"Volkan Cevher","orcid":null},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Volkan Cevher","raw_affiliation_strings":["Electrical and Computer Engineering Department, Rice University, Houston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Rice University, Houston","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.3747,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.97237729,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"37","issue":"3","first_page":"123","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5015000104904175,"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":0.5015000104904175,"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/T13553","display_name":"Age of Information Optimization","score":0.04600000008940697,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.03709999844431877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8521999716758728},{"id":"https://openalex.org/keywords/limelight","display_name":"Limelight","score":0.8137000203132629},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.506600022315979},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.3855000138282776},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.36390000581741333},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3253999948501587}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8521999716758728},{"id":"https://openalex.org/C2777020284","wikidata":"https://www.wikidata.org/wiki/Q555987","display_name":"Limelight","level":2,"score":0.8137000203132629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717000246047974},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.506600022315979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4742000102996826},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C10558101","wikidata":"https://www.wikidata.org/wiki/Q689855","display_name":"Smart grid","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2590000033378601},{"id":"https://openalex.org/C2777913456","wikidata":"https://www.wikidata.org/wiki/Q2981107","display_name":"Smart power","level":3,"score":0.2574000060558319}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/msp.2020.2976000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2020.2976000","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"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 Signal Processing Magazine","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1912.00498","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.00498","pdf_url":"https://arxiv.org/pdf/1912.00498","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"},{"id":"pmh:oai:infoscience.epfl.ch:277714","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/277714","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"research article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1912.00498","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.00498","pdf_url":"https://arxiv.org/pdf/1912.00498","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":43,"referenced_works":["https://openalex.org/W1571416372","https://openalex.org/W1579184372","https://openalex.org/W1646707810","https://openalex.org/W1918371733","https://openalex.org/W2009303086","https://openalex.org/W2022948311","https://openalex.org/W2027648864","https://openalex.org/W2075268401","https://openalex.org/W2088956500","https://openalex.org/W2096145798","https://openalex.org/W2099618002","https://openalex.org/W2107338086","https://openalex.org/W2114791779","https://openalex.org/W2119717200","https://openalex.org/W2121792381","https://openalex.org/W2130263842","https://openalex.org/W2137435346","https://openalex.org/W2139418546","https://openalex.org/W2144672231","https://openalex.org/W2145339207","https://openalex.org/W2165744313","https://openalex.org/W2504148212","https://openalex.org/W2763533254","https://openalex.org/W2962775700","https://openalex.org/W2962856794","https://openalex.org/W2963658727","https://openalex.org/W4214717370","https://openalex.org/W4240558668","https://openalex.org/W6633472260","https://openalex.org/W6635285615","https://openalex.org/W6638018090","https://openalex.org/W6675478397","https://openalex.org/W6675811377","https://openalex.org/W6684488654","https://openalex.org/W6732811253","https://openalex.org/W6734678876","https://openalex.org/W6735011893","https://openalex.org/W6740710678","https://openalex.org/W6746636705","https://openalex.org/W6747035473","https://openalex.org/W6751921135","https://openalex.org/W6752164047","https://openalex.org/W6758937863"],"related_works":[],"abstract_inverted_index":{"Fueled":[0],"by":[1],"recent":[2,19],"advances":[3],"in":[4,13,21,27],"deep":[5],"neural":[6],"networks,":[7],"reinforcement":[8],"learning":[9],"(RL)":[10],"has":[11],"been":[12],"the":[14],"limelight":[15],"because":[16],"of":[17],"many":[18,41,47],"breakthroughs":[20],"artificial":[22],"intelligence,":[23],"including":[24],"defeating":[25],"humans":[26],"games":[28],"(e.g.,":[29],"chess,":[30],"Go,":[31],"StarCraft),":[32],"self-driving":[33],"cars,":[34],"smart-home":[35],"automation,":[36],"and":[37,68],"service":[38],"robots,":[39],"among":[40],"others.":[42],"Despite":[43],"these":[44],"remarkable":[45],"achievements,":[46],"basic":[48],"tasks":[49],"can":[50],"still":[51],"elude":[52],"a":[53],"single":[54],"RL":[55],"agent.":[56],"Examples":[57],"abound,":[58],"from":[59],"multiplayer":[60],"games,":[61],"multirobots,":[62],"cellular-antenna":[63],"tilt":[64],"control,":[65],"traffic-control":[66],"systems,":[67],"smart":[69],"power":[70],"grids":[71],"to":[72],"network":[73],"management.":[74]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2020-05-13T00:00:00"}