{"id":"https://openalex.org/W4229714169","doi":"https://doi.org/10.1561/2600000022","title":"Synchronous Reinforcement Learning-Based Control for Cognitive Autonomy","display_name":"Synchronous Reinforcement Learning-Based Control for Cognitive Autonomy","publication_year":2020,"publication_date":"2020-11-12","ids":{"openalex":"https://openalex.org/W4229714169","doi":"https://doi.org/10.1561/2600000022"},"language":"en","primary_location":{"id":"doi:10.1561/2600000022","is_oa":false,"landing_page_url":"https://doi.org/10.1561/2600000022","pdf_url":null,"source":{"id":"https://openalex.org/S4210220164","display_name":"Foundations and Trends\u00ae in Systems and Control","issn_l":"2325-6818","issn":["2325-6818","2325-6826"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318575","host_organization_name":"Now Publishers","host_organization_lineage":["https://openalex.org/P4310318575"],"host_organization_lineage_names":["Now Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations and Trends\u00ae in Systems and 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/A5040301558","display_name":"Kyriakos G. Vamvoudakis","orcid":"https://orcid.org/0000-0003-1978-4848"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kyriakos G. Vamvoudakis","raw_affiliation_strings":["Georgia Institute of Technology ,","Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology ,","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001552716","display_name":"Nick-Marios T. Kokolakis","orcid":"https://orcid.org/0000-0001-6032-1699"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nick-Marios T. Kokolakis","raw_affiliation_strings":["Georgia Institute of Technology ,","Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology ,","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040301558"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.2561,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.79184415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"8","issue":"1-2","first_page":"1","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.890500009059906,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.890500009059906,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7711068391799927},{"id":"https://openalex.org/keywords/autonomy","display_name":"Autonomy","score":0.6353319883346558},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5307989716529846},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5064729452133179},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.4968896210193634},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4283078908920288},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4163901209831238},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.36496078968048096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22104772925376892},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13977158069610596},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.13183674216270447},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.1286822259426117}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7711068391799927},{"id":"https://openalex.org/C65414064","wikidata":"https://www.wikidata.org/wiki/Q484105","display_name":"Autonomy","level":2,"score":0.6353319883346558},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5307989716529846},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5064729452133179},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4968896210193634},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4283078908920288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4163901209831238},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.36496078968048096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22104772925376892},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13977158069610596},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.13183674216270447},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.1286822259426117},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1561/2600000022","is_oa":false,"landing_page_url":"https://doi.org/10.1561/2600000022","pdf_url":null,"source":{"id":"https://openalex.org/S4210220164","display_name":"Foundations and Trends\u00ae in Systems and Control","issn_l":"2325-6818","issn":["2325-6818","2325-6826"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318575","host_organization_name":"Now Publishers","host_organization_lineage":["https://openalex.org/P4310318575"],"host_organization_lineage_names":["Now Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations and Trends\u00ae in Systems and Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":127,"referenced_works":["https://openalex.org/W81847036","https://openalex.org/W1602326725","https://openalex.org/W1614417283","https://openalex.org/W1630241696","https://openalex.org/W1891098503","https://openalex.org/W1965864832","https://openalex.org/W1968908471","https://openalex.org/W1969705022","https://openalex.org/W1973001558","https://openalex.org/W1973039793","https://openalex.org/W1973378833","https://openalex.org/W1978518835","https://openalex.org/W1983523797","https://openalex.org/W1990005421","https://openalex.org/W1991927580","https://openalex.org/W1997603681","https://openalex.org/W1998151680","https://openalex.org/W1998361253","https://openalex.org/W1999254175","https://openalex.org/W2002373723","https://openalex.org/W2010152647","https://openalex.org/W2011150195","https://openalex.org/W2012451615","https://openalex.org/W2013895638","https://openalex.org/W2019338681","https://openalex.org/W2019478222","https://openalex.org/W2024303516","https://openalex.org/W2027197837","https://openalex.org/W2032085216","https://openalex.org/W2032631296","https://openalex.org/W2035608030","https://openalex.org/W2037025184","https://openalex.org/W2040158468","https://openalex.org/W2041833126","https://openalex.org/W2046376809","https://openalex.org/W2046972933","https://openalex.org/W2047337966","https://openalex.org/W2054973458","https://openalex.org/W2058626062","https://openalex.org/W2068627087","https://openalex.org/W2068949505","https://openalex.org/W2069746367","https://openalex.org/W2078977470","https://openalex.org/W2085194340","https://openalex.org/W2085821433","https://openalex.org/W2086977346","https://openalex.org/W2087063454","https://openalex.org/W2088077079","https://openalex.org/W2088680241","https://openalex.org/W2091265430","https://openalex.org/W2093831009","https://openalex.org/W2094383674","https://openalex.org/W2098000427","https://openalex.org/W2099175737","https://openalex.org/W2099618002","https://openalex.org/W2100827217","https://openalex.org/W2101786389","https://openalex.org/W2104142951","https://openalex.org/W2104843094","https://openalex.org/W2107396783","https://openalex.org/W2107726111","https://openalex.org/W2108286682","https://openalex.org/W2108383324","https://openalex.org/W2109640889","https://openalex.org/W2113501460","https://openalex.org/W2114765979","https://openalex.org/W2116601658","https://openalex.org/W2120038868","https://openalex.org/W2125256511","https://openalex.org/W2137983211","https://openalex.org/W2141042444","https://openalex.org/W2142640215","https://openalex.org/W2146890818","https://openalex.org/W2147750403","https://openalex.org/W2148439597","https://openalex.org/W2151966330","https://openalex.org/W2152161277","https://openalex.org/W2160643434","https://openalex.org/W2163569945","https://openalex.org/W2165744313","https://openalex.org/W2169742265","https://openalex.org/W2249513906","https://openalex.org/W2264897026","https://openalex.org/W2291165559","https://openalex.org/W2312229020","https://openalex.org/W2313875766","https://openalex.org/W2314983263","https://openalex.org/W2319074362","https://openalex.org/W2460713275","https://openalex.org/W2478654971","https://openalex.org/W2480536132","https://openalex.org/W2484957131","https://openalex.org/W2498694880","https://openalex.org/W2509783950","https://openalex.org/W2518470966","https://openalex.org/W2538000344","https://openalex.org/W2570494446","https://openalex.org/W2579592432","https://openalex.org/W2583050531","https://openalex.org/W2585472245","https://openalex.org/W2593263173","https://openalex.org/W2609681974","https://openalex.org/W2609750639","https://openalex.org/W2740197008","https://openalex.org/W2767059073","https://openalex.org/W2792150900","https://openalex.org/W2794212992","https://openalex.org/W2798500587","https://openalex.org/W2800330509","https://openalex.org/W2802027610","https://openalex.org/W2822752092","https://openalex.org/W2887344203","https://openalex.org/W2887582187","https://openalex.org/W2927564896","https://openalex.org/W2962910407","https://openalex.org/W2963609304","https://openalex.org/W3012156918","https://openalex.org/W3012549560","https://openalex.org/W3013559981","https://openalex.org/W3122364233","https://openalex.org/W3122810675","https://openalex.org/W3201048512","https://openalex.org/W4211043782","https://openalex.org/W4231017914","https://openalex.org/W4234761190","https://openalex.org/W4249154916","https://openalex.org/W4253730333"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2107890255","https://openalex.org/W2089013912","https://openalex.org/W2106552856","https://openalex.org/W2076061571","https://openalex.org/W2038908348","https://openalex.org/W1987513656","https://openalex.org/W2145821588"],"abstract_inverted_index":{"This":[0],"monograph":[1],"provides":[2],"an":[3,148,159],"exposition":[4],"of":[5,91,116,151,158,168,178],"recently":[6],"developed":[7,20],"reinforcement":[8,118,169],"learning-based":[9],"techniques":[10,97],"for":[11,66,98],"decision":[12],"and":[13,31,45,50,69,94,101,145,174],"control":[14,65],"in":[15,63,70,76,161],"human-engineered":[16],"cognitive":[17,114],"systems.":[18],"The":[19],"methods":[21],"learn":[22],"the":[23,42,113,137,156],"solution":[24],"to":[25,60,87,111,123,132,171],"optimal":[26,99,102,152],"control,":[27],"zero-sum,":[28,30],"non":[29],"graphical":[32],"game":[33],"problems":[34],"completely":[35],"online":[36],"by":[37],"using":[38],"measured":[39],"data":[40],"along":[41],"system":[43],"trajectories":[44],"have":[46,57,141],"proved":[47],"stability,":[48],"optimality,":[49],"robustness.":[51],"It":[52],"is":[53],"true":[54],"that":[55,154],"games":[56,135],"been":[58],"shown":[59],"be":[61],"important":[62],"robust":[64],"disturbance":[67],"rejection,":[68],"coordinating":[71],"activities":[72],"among":[73],"multiple":[74],"agents":[75,140],"networked":[77],"teams.":[78],"We":[79,104],"also":[80,105],"consider":[81],"cases":[82],"with":[83],"intermittent":[84],"(an":[85],"analogous":[86],"triggered":[88],"control)":[89],"instead":[90],"continuous":[92],"learning":[93,119,139,170],"apply":[95],"those":[96],"regulation":[100],"tracking.":[103],"introduce":[106,147],"a":[107,117],"bounded":[108,179],"rational":[109,180],"model":[110],"quantify":[112],"skills":[115],"agent.":[120],"In":[121],"order":[122],"do":[124],"that,":[125],"we":[126,146,165],"leverage":[127],"ideas":[128],"from":[129],"behavioral":[130],"psychology":[131],"formulate":[133],"differential":[134],"where":[136],"interacting":[138],"different":[142],"intelligence":[143],"skills,":[144],"iterative":[149],"method":[150],"responses":[153],"determine":[155],"policy":[157],"agent":[160],"adversarial":[162],"environments.":[163],"Finally,":[164],"present":[166],"applications":[167],"motion":[172],"planning":[173],"collaborative":[175],"target":[176],"tracking":[177],"unmanned":[181],"aerial":[182],"vehicles.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}