{"id":"https://openalex.org/W3120786689","doi":"https://doi.org/10.1109/cdc42340.2020.9304242","title":"Adaptive Control for Linearizable Systems Using On-Policy Reinforcement Learning","display_name":"Adaptive Control for Linearizable Systems Using On-Policy Reinforcement Learning","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3120786689","doi":"https://doi.org/10.1109/cdc42340.2020.9304242","mag":"3120786689"},"language":"en","primary_location":{"id":"doi:10.1109/cdc42340.2020.9304242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9304242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://authors.library.caltech.edu/110732/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085796854","display_name":"Tyler Westenbroek","orcid":"https://orcid.org/0000-0003-1111-3118"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tyler Westenbroek","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089549365","display_name":"Eric Mazumdar","orcid":"https://orcid.org/0000-0002-1815-269X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Mazumdar","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070827615","display_name":"David Fridovich-Keil","orcid":"https://orcid.org/0000-0002-5866-6441"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Fridovich-Keil","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039259042","display_name":"Valmik Prabhu","orcid":"https://orcid.org/0000-0002-5059-5407"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Valmik Prabhu","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045155646","display_name":"Claire J. Tomlin","orcid":"https://orcid.org/0000-0003-3192-3185"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claire J. Tomlin","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103101043","display_name":"S. Shankar Sastry","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Shankar Sastry","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5085796854"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.7219,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77961423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9990000128746033,"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":0.9851999878883362,"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/control-theory","display_name":"Control theory (sociology)","score":0.7139986753463745},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6599025130271912},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6459207534790039},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.6209177374839783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5865994095802307},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.551213264465332},{"id":"https://openalex.org/keywords/linearization","display_name":"Linearization","score":0.46808844804763794},{"id":"https://openalex.org/keywords/pendulum","display_name":"Pendulum","score":0.46674710512161255},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.43723487854003906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2751843333244324},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.22513633966445923},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.21926045417785645},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1956728994846344},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12583470344543457}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7139986753463745},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6599025130271912},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6459207534790039},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.6209177374839783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5865994095802307},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.551213264465332},{"id":"https://openalex.org/C11210021","wikidata":"https://www.wikidata.org/wiki/Q1520713","display_name":"Linearization","level":3,"score":0.46808844804763794},{"id":"https://openalex.org/C110639684","wikidata":"https://www.wikidata.org/wiki/Q20702","display_name":"Pendulum","level":2,"score":0.46674710512161255},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.43723487854003906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2751843333244324},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.22513633966445923},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.21926045417785645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1956728994846344},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12583470344543457},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc42340.2020.9304242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9304242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:authors.library.caltech.edu:110732","is_oa":true,"landing_page_url":"https://authors.library.caltech.edu/110732/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"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":"Book Section"}],"best_oa_location":{"id":"pmh:oai:authors.library.caltech.edu:110732","is_oa":true,"landing_page_url":"https://authors.library.caltech.edu/110732/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"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":"Book Section"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W594357522","https://openalex.org/W1191599655","https://openalex.org/W1515851193","https://openalex.org/W1561445488","https://openalex.org/W1572161815","https://openalex.org/W1771410628","https://openalex.org/W1983523797","https://openalex.org/W2039671349","https://openalex.org/W2069529194","https://openalex.org/W2083483041","https://openalex.org/W2097121541","https://openalex.org/W2115932303","https://openalex.org/W2116243329","https://openalex.org/W2116383462","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2122136962","https://openalex.org/W2141702858","https://openalex.org/W2143803054","https://openalex.org/W2148053762","https://openalex.org/W2155027007","https://openalex.org/W2157577161","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2561116802","https://openalex.org/W2736601468","https://openalex.org/W2787248994","https://openalex.org/W2963864421","https://openalex.org/W2982443224","https://openalex.org/W3014528414","https://openalex.org/W4250954493","https://openalex.org/W4287817121","https://openalex.org/W4302570325","https://openalex.org/W4391410851","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6677183884","https://openalex.org/W6681183203","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6741002519","https://openalex.org/W6769289699","https://openalex.org/W6775640803"],"related_works":["https://openalex.org/W962423920","https://openalex.org/W2387968248","https://openalex.org/W2350715914","https://openalex.org/W2101175215","https://openalex.org/W2379529020","https://openalex.org/W2120821724","https://openalex.org/W2893549521","https://openalex.org/W2352322616","https://openalex.org/W2124140241","https://openalex.org/W2574438335"],"abstract_inverted_index":{"This":[0,54],"paper":[1],"proposes":[2],"a":[3,8,125,135],"framework":[4],"for":[5,13,67],"adaptively":[6],"learning":[7,78,102],"feedback":[9],"linearization-based":[10],"tracking":[11,117],"controller":[12,66],"an":[14],"unknown":[15],"system":[16,69,79],"using":[17],"discrete-time":[18],"model-free":[19],"policy-gradient":[20],"parameter":[21,119],"update":[22],"rules.":[23],"The":[24,76],"primary":[25],"advantage":[26],"of":[27,52,58,87,128,134,141],"the":[28,42,56,64,68,84,88,100,116,139,142],"scheme":[29],"over":[30],"standard":[31,126],"model-reference":[32],"adaptive":[33,108],"control":[34,109],"techniques":[35,96],"is":[36,80],"that":[37,112],"it":[38],"does":[39],"not":[40],"require":[41],"learned":[43],"inverse":[44],"model":[45],"to":[46,62,72,83,110],"be":[47],"invertible":[48],"at":[49],"all":[50],"instances":[51],"time.":[53],"enables":[55],"use":[57],"general":[59],"function":[60],"approximators":[61],"approximate":[63],"linearizing":[65],"without":[70],"having":[71],"worry":[73],"about":[74],"singularities.":[75],"overall":[77],"stochastic,":[81],"due":[82],"random":[85],"nature":[86],"policy":[89],"gradient":[90],"updates,":[91],"thus":[92],"we":[93],"combine":[94],"analysis":[95],"commonly":[97],"employed":[98],"in":[99],"machine":[101],"literature":[103],"alongside":[104],"stability":[105],"arguments":[106],"from":[107],"demonstrate":[111],"with":[113],"high":[114],"probability":[115],"and":[118],"errors":[120],"concentrate":[121],"near":[122],"zero,":[123],"under":[124],"persistency":[127],"excitation":[129],"condition.":[130],"A":[131],"simulated":[132],"example":[133],"double":[136],"pendulum":[137],"demonstrates":[138],"utility":[140],"proposed":[143],"theory.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
