{"id":"https://openalex.org/W3010713425","doi":"https://doi.org/10.1109/cdc40024.2019.9029500","title":"Reinforcement Learning with Sparse Bellman Error Extrapolation for Infinite-Horizon Approximate Optimal Regulation","display_name":"Reinforcement Learning with Sparse Bellman Error Extrapolation for Infinite-Horizon Approximate Optimal Regulation","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3010713425","doi":"https://doi.org/10.1109/cdc40024.2019.9029500","mag":"3010713425"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9029500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-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/A5027840499","display_name":"Max L. Greene","orcid":"https://orcid.org/0000-0003-2733-0344"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Max L. Greene","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018956236","display_name":"Patryk Deptula","orcid":"https://orcid.org/0000-0002-2328-9148"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patryk Deptula","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045042598","display_name":"Scott Nivison","orcid":"https://orcid.org/0000-0002-5738-2535"},"institutions":[{"id":"https://openalex.org/I2801461044","display_name":"Eglin Air Force Base","ror":"https://ror.org/002c7zk35","country_code":"US","type":"government","lineage":["https://openalex.org/I1330347796","https://openalex.org/I2801461044","https://openalex.org/I4210089612","https://openalex.org/I4210102105"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Nivison","raw_affiliation_strings":["Munitions Directorate, Air Force Research Laboratory, Eglin AFB, FL, USA"],"affiliations":[{"raw_affiliation_string":"Munitions Directorate, Air Force Research Laboratory, Eglin AFB, FL, USA","institution_ids":["https://openalex.org/I2801461044"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032651215","display_name":"Warren E. Dixon","orcid":"https://orcid.org/0000-0002-5091-181X"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Warren E. Dixon","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027840499"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":0.7759,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.76132384,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"2","issue":null,"first_page":"1959","last_page":"1964"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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":1.0,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9911999702453613,"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"}},{"id":"https://openalex.org/T12277","display_name":"Frequency Control in Power Systems","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.7126377820968628},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6044297218322754},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5746688842773438},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5300381183624268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5157065987586975},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.48164573311805725},{"id":"https://openalex.org/keywords/classification-of-discontinuities","display_name":"Classification of discontinuities","score":0.47498005628585815},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.47351741790771484},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4703502953052521},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.45827364921569824},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4495851993560791},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3872396945953369},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3575778305530548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2558947503566742},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.1398959755897522}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7126377820968628},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6044297218322754},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5746688842773438},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5300381183624268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5157065987586975},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.48164573311805725},{"id":"https://openalex.org/C15627037","wikidata":"https://www.wikidata.org/wiki/Q541961","display_name":"Classification of discontinuities","level":2,"score":0.47498005628585815},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47351741790771484},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4703502953052521},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.45827364921569824},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4495851993560791},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3872396945953369},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3575778305530548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2558947503566742},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.1398959755897522},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc40024.2019.9029500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W560518094","https://openalex.org/W1483858097","https://openalex.org/W1540245649","https://openalex.org/W1559107966","https://openalex.org/W1793264465","https://openalex.org/W1968908471","https://openalex.org/W1977237536","https://openalex.org/W1977671496","https://openalex.org/W1983523797","https://openalex.org/W2002007892","https://openalex.org/W2003183707","https://openalex.org/W2013895638","https://openalex.org/W2048687352","https://openalex.org/W2085194340","https://openalex.org/W2086975818","https://openalex.org/W2093831009","https://openalex.org/W2097253853","https://openalex.org/W2098035803","https://openalex.org/W2098432798","https://openalex.org/W2104843094","https://openalex.org/W2108665656","https://openalex.org/W2109987654","https://openalex.org/W2111034649","https://openalex.org/W2113501460","https://openalex.org/W2113606819","https://openalex.org/W2116479681","https://openalex.org/W2120249358","https://openalex.org/W2150514620","https://openalex.org/W2150841368","https://openalex.org/W2156387975","https://openalex.org/W2165726932","https://openalex.org/W2296093392","https://openalex.org/W2314983263","https://openalex.org/W2396603033","https://openalex.org/W2476930474","https://openalex.org/W2531648764","https://openalex.org/W2569832271","https://openalex.org/W2570540139","https://openalex.org/W2734677971","https://openalex.org/W2766918150","https://openalex.org/W2781919638","https://openalex.org/W2782694651","https://openalex.org/W2790688051","https://openalex.org/W2795039172","https://openalex.org/W2800330509","https://openalex.org/W2887138972","https://openalex.org/W2887252040","https://openalex.org/W2899349726","https://openalex.org/W2912316379","https://openalex.org/W2963093491","https://openalex.org/W3213472335","https://openalex.org/W4214717370","https://openalex.org/W4238000550","https://openalex.org/W4301747304","https://openalex.org/W6676903177","https://openalex.org/W6682889407","https://openalex.org/W6712222499","https://openalex.org/W6804409665"],"related_works":["https://openalex.org/W4239477580","https://openalex.org/W2367526667","https://openalex.org/W4320083357","https://openalex.org/W2320719555","https://openalex.org/W2158581961","https://openalex.org/W2964126589","https://openalex.org/W2280099822","https://openalex.org/W2347563025","https://openalex.org/W2107530459","https://openalex.org/W2773917197"],"abstract_inverted_index":{"This":[0],"paper":[1],"provides":[2],"an":[3,93],"approximate":[4],"online":[5],"adaptive":[6],"solution":[7],"to":[8,36,63,81,91],"the":[9,40,64,76,83,102,108,127,133,147,151],"infinite-horizon":[10],"optimal":[11,94],"control":[12],"problem":[13],"for":[14,51,96],"control-affine":[15],"continuous-time":[16],"nonlinear":[17],"systems.":[18],"The":[19],"state-space":[20],"is":[21,124,141],"segmented":[22],"into":[23],"a":[24,49,118],"user-defined":[25],"number":[26,66],"of":[27,39,67,121,146,153],"segments.":[28],"Off-policy":[29],"trajectories":[30,78],"are":[31,70,79,105],"selected":[32],"over":[33],"each":[34,73,97,100,116],"segment":[35,117],"facilitate":[37],"learning":[38],"value":[41,109],"function":[42,110],"weight":[43,111,134],"estimates.":[44],"Sparse":[45],"neural":[46],"networks":[47],"enable":[48],"framework":[50],"switching":[52],"and":[53],"state":[54],"space":[55],"segmentation":[56],"as":[57,59],"well":[58],"computational":[60],"benefits":[61],"due":[62],"small":[65],"neurons":[68],"that":[69],"active.":[71],"At":[72],"sparse":[74],"segment,":[75,101],"off-policy":[77],"used":[80,106,125],"extrapolate":[82],"Bellman":[84],"error":[85],"(BE)":[86],"across":[87],"their":[88],"respective":[89],"segments":[90],"provide":[92],"policy":[95],"segment.":[98],"Over":[99],"extrapolated":[103,122],"BEs":[104,123],"in":[107,126,132,150],"update":[112,128,135],"laws.":[113,136],"Because":[114],"at":[115],"different":[119],"set":[120],"laws,":[129],"discontinuities":[130],"occur":[131],"A":[137],"Lyapunov-like":[138],"stability":[139],"analysis":[140],"included":[142],"which":[143],"proves":[144],"boundedness":[145],"overall":[148],"system":[149],"presence":[152],"discontinuities.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}