{"id":"https://openalex.org/W4380029562","doi":"https://doi.org/10.1109/icit58465.2023.10143150","title":"Reinforcement learning of LQR control policy by a double inverted-pendulum biomechanical model","display_name":"Reinforcement learning of LQR control policy by a double inverted-pendulum biomechanical model","publication_year":2023,"publication_date":"2023-04-04","ids":{"openalex":"https://openalex.org/W4380029562","doi":"https://doi.org/10.1109/icit58465.2023.10143150"},"language":"en","primary_location":{"id":"doi:10.1109/icit58465.2023.10143150","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icit58465.2023.10143150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Industrial Technology (ICIT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5068395409","display_name":"Kamran Iqbal","orcid":"https://orcid.org/0000-0001-8375-290X"},"institutions":[{"id":"https://openalex.org/I102401767","display_name":"University of Arkansas at Little Rock","ror":"https://ror.org/04fttyv97","country_code":"US","type":"education","lineage":["https://openalex.org/I102401767"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kamran Iqbal","raw_affiliation_strings":["University of Arkansas at Little Rock,Little Rock,Arkansas,72204"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arkansas at Little Rock,Little Rock,Arkansas,72204","institution_ids":["https://openalex.org/I102401767"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039219127","display_name":"Muhammad Haras","orcid":null},"institutions":[{"id":"https://openalex.org/I102401767","display_name":"University of Arkansas at Little Rock","ror":"https://ror.org/04fttyv97","country_code":"US","type":"education","lineage":["https://openalex.org/I102401767"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhammad Haras","raw_affiliation_strings":["University of Arkansas at Little Rock,Little Rock,Arkansas,72204"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arkansas at Little Rock,Little Rock,Arkansas,72204","institution_ids":["https://openalex.org/I102401767"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102401767"],"apc_list":null,"apc_paid":null,"fwci":1.8889,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84700168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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":0.9997000098228455,"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9273999929428101,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.800861656665802},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.7628908157348633},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6750800609588623},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6502178907394409},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.6001970767974854},{"id":"https://openalex.org/keywords/algebraic-riccati-equation","display_name":"Algebraic Riccati equation","score":0.5854694247245789},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5349646210670471},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.50246262550354},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4842069149017334},{"id":"https://openalex.org/keywords/double-pendulum","display_name":"Double pendulum","score":0.4787413477897644},{"id":"https://openalex.org/keywords/riccati-equation","display_name":"Riccati equation","score":0.47012555599212646},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4472711980342865},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.43602487444877625},{"id":"https://openalex.org/keywords/matlab","display_name":"MATLAB","score":0.4280869960784912},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37089163064956665},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34731268882751465},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.28005245327949524},{"id":"https://openalex.org/keywords/differential-equation","display_name":"Differential equation","score":0.1582549810409546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12896868586540222}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.800861656665802},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.7628908157348633},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6750800609588623},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6502178907394409},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.6001970767974854},{"id":"https://openalex.org/C13847129","wikidata":"https://www.wikidata.org/wiki/Q4723989","display_name":"Algebraic Riccati equation","level":4,"score":0.5854694247245789},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5349646210670471},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.50246262550354},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4842069149017334},{"id":"https://openalex.org/C167183279","wikidata":"https://www.wikidata.org/wiki/Q1243208","display_name":"Double pendulum","level":4,"score":0.4787413477897644},{"id":"https://openalex.org/C45473103","wikidata":"https://www.wikidata.org/wiki/Q851503","display_name":"Riccati equation","level":3,"score":0.47012555599212646},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4472711980342865},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.43602487444877625},{"id":"https://openalex.org/C2780365114","wikidata":"https://www.wikidata.org/wiki/Q169478","display_name":"MATLAB","level":2,"score":0.4280869960784912},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37089163064956665},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34731268882751465},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28005245327949524},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.1582549810409546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12896868586540222},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icit58465.2023.10143150","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icit58465.2023.10143150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Industrial Technology (ICIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310058","display_name":"University of Arkansas","ror":"https://ror.org/05jbt9m15"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1510487468","https://openalex.org/W1513689897","https://openalex.org/W1601081659","https://openalex.org/W1626155273","https://openalex.org/W1825869920","https://openalex.org/W1907796993","https://openalex.org/W1972809999","https://openalex.org/W1979772489","https://openalex.org/W2024303516","https://openalex.org/W2037025184","https://openalex.org/W2050838777","https://openalex.org/W2094666332","https://openalex.org/W2147170031","https://openalex.org/W2148439597","https://openalex.org/W2152161277","https://openalex.org/W2156737235","https://openalex.org/W2165726932","https://openalex.org/W2570494446","https://openalex.org/W2907944110","https://openalex.org/W2923675576","https://openalex.org/W3043164720","https://openalex.org/W3169248275","https://openalex.org/W3216311662","https://openalex.org/W4304142216","https://openalex.org/W6683195989"],"related_works":["https://openalex.org/W2005019312","https://openalex.org/W2547959172","https://openalex.org/W2018296362","https://openalex.org/W2727200542","https://openalex.org/W2002357820","https://openalex.org/W197349956","https://openalex.org/W2997206142","https://openalex.org/W2027962246","https://openalex.org/W2804494800","https://openalex.org/W2116228702"],"abstract_inverted_index":{"Optimal":[0],"LQR":[1,100],"feedback":[2,42],"gains":[3,43],"can":[4],"be":[5],"learned":[6],"using":[7,17],"reinforcement":[8,38],"learning":[9,39],"(RL)":[10],"framework":[11],"for":[12],"systems":[13,30],"with":[14],"unknown":[15],"dynamics":[16],"policy":[18,22],"iteration":[19,23],"methods.":[20],"However,":[21],"in":[24,44,65,83,106],"the":[25,45,60,90,93,99,107,121],"case":[26,46,108],"of":[27,40,47,109],"inherently":[28,111],"unstable":[29,112],"becomes":[31],"challenging.":[32],"In":[33],"this":[34],"study":[35],"we":[36],"establish":[37],"optimal":[41],"a":[48],"nonlinear":[49],"double":[50],"inverted-pendulum":[51],"(DIP)":[52],"biomechanical":[53,61],"model.":[54],"Using":[55],"an":[56,110],"admissible":[57],"initial":[58],"policy,":[59],"model":[62],"was":[63],"simulated":[64],"MATLAB":[66],"and":[67,81,119],"trajectory":[68],"data":[69],"were":[70,75],"recorded.":[71],"The":[72,102],"state":[73],"variables":[74],"transformed":[76],"to":[77,88,92,123,127],"quadratic":[78],"basis":[79],"function":[80],"used":[82],"approximate":[84],"dynamic":[85],"programming":[86],"(ADP)":[87],"learn":[89],"solution":[91],"algebraic":[94],"Riccati":[95],"equation":[96],"(ARE)":[97],"underlying":[98],"problem.":[101],"RL":[103,125],"results":[104],"obtained":[105],"DIP":[113],"system":[114],"indicate":[115],"relatively":[116],"fast":[117],"convergence":[118],"demonstrate":[120],"potential":[122],"apply":[124],"techniques":[126],"more":[128],"complex":[129],"systems.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}