{"id":"https://openalex.org/W3150527705","doi":"https://doi.org/10.1109/cdc45484.2021.9683641","title":"Online Policies for Real-Time Control Using MRAC-RL","display_name":"Online Policies for Real-Time Control Using MRAC-RL","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W3150527705","doi":"https://doi.org/10.1109/cdc45484.2021.9683641","mag":"3150527705"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9683641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683641","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","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":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.16551","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088586087","display_name":"Anubhav Guha","orcid":"https://orcid.org/0000-0002-9668-6101"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anubhav Guha","raw_affiliation_strings":["Massachusetts Institute of Technology,Department of Mechanical Engineering,Cambridge,MA,USA,02139","Massachusetts Institute Of Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Department of Mechanical Engineering,Cambridge,MA,USA,02139","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082528518","display_name":"Anuradha M. Annaswamy","orcid":"https://orcid.org/0000-0002-4354-0459"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anuradha M. Annaswamy","raw_affiliation_strings":["Massachusetts Institute of Technology,Department of Mechanical Engineering,Cambridge,MA,USA,02139","Massachusetts Institute Of Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Department of Mechanical Engineering,Cambridge,MA,USA,02139","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088586087"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.34502683,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39049826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1808","last_page":"1813"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8501123189926147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7245104312896729},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.6434038877487183},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6325536966323853},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6105675101280212},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.49298521876335144},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.48053106665611267},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47961530089378357},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47124984860420227},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4217432141304016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2948683500289917},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13701888918876648},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13559895753860474},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0762777030467987}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8501123189926147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245104312896729},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.6434038877487183},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6325536966323853},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6105675101280212},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.49298521876335144},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.48053106665611267},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47961530089378357},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47124984860420227},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4217432141304016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2948683500289917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13701888918876648},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13559895753860474},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0762777030467987},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cdc45484.2021.9683641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683641","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","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":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.16551","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.16551","pdf_url":"https://arxiv.org/pdf/2103.16551","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3150527705","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.16551.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2103.16551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.16551","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.16551","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.16551","pdf_url":"https://arxiv.org/pdf/2103.16551","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3150527705.pdf","grobid_xml":"https://content.openalex.org/works/W3150527705.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1572161815","https://openalex.org/W1949804828","https://openalex.org/W1977655452","https://openalex.org/W1980185469","https://openalex.org/W1990005421","https://openalex.org/W2043151145","https://openalex.org/W2051846963","https://openalex.org/W2058729559","https://openalex.org/W2067603665","https://openalex.org/W2089087399","https://openalex.org/W2106228772","https://openalex.org/W2107726111","https://openalex.org/W2109191523","https://openalex.org/W2117799976","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2529477964","https://openalex.org/W2602963933","https://openalex.org/W2618318883","https://openalex.org/W2736601468","https://openalex.org/W2739083961","https://openalex.org/W2751801093","https://openalex.org/W2754517384","https://openalex.org/W2787908307","https://openalex.org/W2798273187","https://openalex.org/W2822752092","https://openalex.org/W2898436992","https://openalex.org/W2898758998","https://openalex.org/W2953708620","https://openalex.org/W2962749646","https://openalex.org/W2962974944","https://openalex.org/W2963184939","https://openalex.org/W2963305465","https://openalex.org/W2963641140","https://openalex.org/W2964182728","https://openalex.org/W2965194460","https://openalex.org/W2973076431","https://openalex.org/W2982095652","https://openalex.org/W3036766693","https://openalex.org/W3045510440","https://openalex.org/W6627932998","https://openalex.org/W6680657880","https://openalex.org/W6684921986","https://openalex.org/W6704571135","https://openalex.org/W6728252718","https://openalex.org/W6734129231","https://openalex.org/W6738483526","https://openalex.org/W6739506316","https://openalex.org/W6741002519","https://openalex.org/W6741977017","https://openalex.org/W6744123322","https://openalex.org/W6755890616","https://openalex.org/W6756103505","https://openalex.org/W6756463683","https://openalex.org/W6766208143","https://openalex.org/W6779878635","https://openalex.org/W6786292401"],"related_works":["https://openalex.org/W2896048729","https://openalex.org/W2909601460","https://openalex.org/W1997318940","https://openalex.org/W2912009712","https://openalex.org/W3208318794","https://openalex.org/W3144645906","https://openalex.org/W3143763398","https://openalex.org/W2930426397","https://openalex.org/W3156965612","https://openalex.org/W3085625411","https://openalex.org/W2974373467","https://openalex.org/W3011994177","https://openalex.org/W3153659300","https://openalex.org/W2899339345","https://openalex.org/W2486087872","https://openalex.org/W1630686938","https://openalex.org/W2157353182","https://openalex.org/W3202294003","https://openalex.org/W3120111328","https://openalex.org/W3126191119"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,154],"propose":[4,107],"the":[5,49,67,123,131,138,157,168],"Model":[6],"Reference":[7],"Adaptive":[8],"Control":[9],"&":[10],"Reinforcement":[11],"Learning":[12],"(MRAC-RL)":[13],"approach":[14,159],"to":[15,37,57,59,92,116],"developing":[16],"online":[17,73,171],"policies":[18,40,56,74],"for":[19,41,130],"systems":[20],"in":[21,26,66,97],"which":[22],"modeling":[23],"errors":[24],"occur":[25],"real-time.":[27],"Although":[28],"reinforcement":[29],"learning":[30],"(RL)":[31],"algorithms":[32,164],"have":[33],"been":[34],"successfully":[35],"used":[36],"develop":[38],"control":[39,125],"dynamical":[42],"systems,":[43,121],"discrepancies":[44],"between":[45],"simulated":[46],"dynamics":[47,52],"and":[48,61,94,135,165],"true":[50],"target":[51,99],"can":[53],"cause":[54],"trained":[55],"fail":[58],"generalize":[60],"adapt":[62,93],"appropriately":[63],"when":[64,102],"deployed":[65],"real-world.":[68],"The":[69],"MRAC-RL":[70,91,158],"framework":[71],"generates":[72],"by":[75],"utilizing":[76],"an":[77,149],"inner-loop":[78],"adaptive":[79,139],"controller":[80],"together":[81],"with":[82],"a":[83,98,108,117,145],"simulation-trained":[84],"outer-loop":[85],"RL":[86,163],"policy.":[87],"This":[88],"structure":[89],"allows":[90],"operate":[95],"effectively":[96],"environment,":[100],"even":[101],"parametric":[103],"uncertainties":[104],"exists.":[105],"We":[106],"set":[109],"of":[110,119,148,170],"novel":[111],"MRAC":[112],"algorithms,":[113],"apply":[114],"them":[115],"class":[118],"nonlinear":[120],"derive":[122],"associated":[124],"laws,":[126],"provide":[127],"stability":[128],"guarantees":[129],"resulting":[132],"closed-loop":[133],"system,":[134],"show":[136],"that":[137,156],"tracking":[140],"objective":[141],"is":[142],"achieved.":[143],"Using":[144],"simulation":[146],"study":[147],"automated":[150],"quadrotor":[151],"landing":[152],"task,":[153],"demonstrate":[155],"improves":[160],"upon":[161],"state-of-the-art":[162],"techniques":[166],"through":[167],"generation":[169],"policies.":[172]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}