{"id":"https://openalex.org/W4387870009","doi":"https://doi.org/10.1109/iwis58789.2023.10284677","title":"A Comparative Study of Reinforcement Learning and Analytical Methods for Optimal Control","display_name":"A Comparative Study of Reinforcement Learning and Analytical Methods for Optimal Control","publication_year":2023,"publication_date":"2023-08-09","ids":{"openalex":"https://openalex.org/W4387870009","doi":"https://doi.org/10.1109/iwis58789.2023.10284677"},"language":"en","primary_location":{"id":"doi:10.1109/iwis58789.2023.10284677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwis58789.2023.10284677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Workshop on Intelligent Systems (IWIS)","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/A5014113437","display_name":"Myeongseok Ryu","orcid":"https://orcid.org/0009-0004-3279-5765"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Myeongseok Ryu","raw_affiliation_strings":["School of Mechanical Engineering, Gwangju Institute of Science and Technology,Gwangju,Republic of Korea","School of Mechanical Engineering, Gwangju Institute of Science and Technology, Gwangju, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Gwangju Institute of Science and Technology,Gwangju,Republic of Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"School of Mechanical Engineering, Gwangju Institute of Science and Technology, Gwangju, Republic of Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113029540","display_name":"Junseo Ha","orcid":null},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junseo Ha","raw_affiliation_strings":["Artificial Intelligence Graduate School, Gwangju Institute of Science and Technology,Gwangju,Republic of Korea","Artificial Intelligence Graduate School, Gwangju Institute of Science and Technology, Gwangju, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Graduate School, Gwangju Institute of Science and Technology,Gwangju,Republic of Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"Artificial Intelligence Graduate School, Gwangju Institute of Science and Technology, Gwangju, Republic of Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104103761","display_name":"Minji Kim","orcid":"https://orcid.org/0009-0005-6441-0441"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minji Kim","raw_affiliation_strings":["School of Mechanical Engineering, Gwangju Institute of Science and Technology,Gwangju,Republic of Korea","School of Mechanical Engineering, Gwangju Institute of Science and Technology, Gwangju, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Gwangju Institute of Science and Technology,Gwangju,Republic of Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"School of Mechanical Engineering, Gwangju Institute of Science and Technology, Gwangju, Republic of Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070417804","display_name":"Kyunghwan Choi","orcid":"https://orcid.org/0000-0002-4832-1597"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyunghwan Choi","raw_affiliation_strings":["School of Mechanical Engineering, Gwangju Institute of Science and Technology,Gwangju,Republic of Korea","School of Mechanical Engineering, Gwangju Institute of Science and Technology, Gwangju, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Gwangju Institute of Science and Technology,Gwangju,Republic of Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"School of Mechanical Engineering, Gwangju Institute of Science and Technology, Gwangju, Republic of Korea","institution_ids":["https://openalex.org/I39534123"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014113437"],"corresponding_institution_ids":["https://openalex.org/I39534123"],"apc_list":null,"apc_paid":null,"fwci":0.2017,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5675639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9976000189781189,"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":0.9778000116348267,"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":0.8672055006027222},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.714641809463501},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6787257194519043},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.674293041229248},{"id":"https://openalex.org/keywords/discounting","display_name":"Discounting","score":0.6702024340629578},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.647470235824585},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6125081777572632},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5743535161018372},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5158190131187439},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45761576294898987},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.41786572337150574},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3981376588344574},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3749174177646637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3537285625934601},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2091682255268097},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16896551847457886}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8672055006027222},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.714641809463501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6787257194519043},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.674293041229248},{"id":"https://openalex.org/C6177178","wikidata":"https://www.wikidata.org/wiki/Q10998070","display_name":"Discounting","level":2,"score":0.6702024340629578},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.647470235824585},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6125081777572632},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5743535161018372},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5158190131187439},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45761576294898987},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.41786572337150574},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3981376588344574},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3749174177646637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3537285625934601},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2091682255268097},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16896551847457886},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwis58789.2023.10284677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwis58789.2023.10284677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Workshop on Intelligent Systems (IWIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1990005421","https://openalex.org/W2111034649","https://openalex.org/W2765650568","https://openalex.org/W4205300464","https://openalex.org/W4298857966","https://openalex.org/W4322754363","https://openalex.org/W6634206955","https://openalex.org/W6637967152","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W962423920","https://openalex.org/W2387968248","https://openalex.org/W2969865478","https://openalex.org/W3121098034","https://openalex.org/W3123359883","https://openalex.org/W2083534175","https://openalex.org/W4360604818","https://openalex.org/W3129036502","https://openalex.org/W2415292238","https://openalex.org/W3034621666"],"abstract_inverted_index":{"Numerous":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"algorithms":[4,135],"have":[5,106],"been":[6],"introduced":[7],"to":[8,25,41,98,128,131],"resolve":[9],"challenging":[10],"tasks":[11],"like":[12],"game":[13],"playing,":[14],"natural":[15],"language":[16],"processing,":[17],"and":[18,50,64,81,85,95,120,136],"control.":[19],"Particularly,":[20],"RL":[21,49,116,134],"can":[22,112],"be":[23,113],"used":[24],"find":[26,42],"a":[27],"good":[28],"policy":[29],"for":[30,33,53,71],"control":[31,37,55,67,76,96,138],"systems":[32],"which":[34],"the":[35,72,100,110],"optimal":[36,54,137],"sequence":[38,97],"is":[39,126],"difficult":[40],"by":[43,115],"analytical":[44,51,73],"methods.":[45,74],"This":[46,123],"paper":[47],"compares":[48],"methods":[52],"in":[56,88],"an":[57],"inverted":[58],"pendulum":[59],"environment.":[60],"Dynamic":[61],"programming":[62],"(DP)":[63],"model":[65],"predictive":[66],"(MPC)":[68],"are":[69,83],"considered":[70],"The":[75],"results":[77],"of":[78,90],"RL,":[79],"DP,":[80],"MPC":[82],"qualitatively":[84],"quantitatively":[86],"compared":[87],"terms":[89],"total":[91],"reward,":[92],"state":[93],"response,":[94],"investigate":[99],"relationships":[101,111],"between":[102],"them.":[103],"Because":[104],"they":[105],"similar":[107],"problem":[108],"formulations,":[109],"explained":[114],"parameters:":[117],"discounting":[118],"factor":[119],"exploration":[121],"rate.":[122],"comparative":[124],"study":[125],"expected":[127],"provide":[129],"insights":[130],"those":[132],"studying":[133],"theories.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
