{"id":"https://openalex.org/W4386275633","doi":"https://doi.org/10.1109/access.2023.3310405","title":"Optimizing Reinforcement Learning Control Model in Furuta Pendulum and Transferring it to Real-World","display_name":"Optimizing Reinforcement Learning Control Model in Furuta Pendulum and Transferring it to Real-World","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386275633","doi":"https://doi.org/10.1109/access.2023.3310405"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3310405","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3310405","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10234431.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10234431.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101369461","display_name":"Myung Rae Hong","orcid":"https://orcid.org/0009-0002-9438-7957"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myung Rae Hong","raw_affiliation_strings":["Department of Mechanical Engineering, Multiscale Bio-Inspired Technology Laboratory, Ajou University, Suwon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Multiscale Bio-Inspired Technology Laboratory, Ajou University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012779975","display_name":"Sanghun Kang","orcid":"https://orcid.org/0000-0003-2690-5644"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanghun Kang","raw_affiliation_strings":["Department of Mechanical Engineering, Multiscale Bio-Inspired Technology Laboratory, Ajou University, Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-2690-5644","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Multiscale Bio-Inspired Technology Laboratory, Ajou University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101590222","display_name":"J Lee","orcid":"https://orcid.org/0000-0002-5783-2583"},"institutions":[{"id":"https://openalex.org/I4210111434","display_name":"Korea Institute of Machinery & Materials","ror":"https://ror.org/01qcq9d74","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I2801339556","https://openalex.org/I4210111434","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I4387152098"]},{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jingoo Lee","raw_affiliation_strings":["Department of Sustainable Environment Research, Korea Institute of Machinery ad Materials, Daejeon, Republic of Korea","Department of Mechanical Engineering, Ajou University, Multiscale Bio-inspired Technology Lab, Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-5783-2583","affiliations":[{"raw_affiliation_string":"Department of Sustainable Environment Research, Korea Institute of Machinery ad Materials, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I4210111434"]},{"raw_affiliation_string":"Department of Mechanical Engineering, Ajou University, Multiscale Bio-inspired Technology Lab, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051216471","display_name":"SungChul Seo","orcid":"https://orcid.org/0000-0001-8301-6355"},"institutions":[{"id":"https://openalex.org/I55188197","display_name":"Seokyeong University","ror":"https://ror.org/04x0k0m51","country_code":"KR","type":"education","lineage":["https://openalex.org/I55188197"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungchul Seo","raw_affiliation_strings":["Department of Nano-Chemical, Biological and Environmental Engineering, Seokyeong University, Seoul, Seongbuk, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-8301-6355","affiliations":[{"raw_affiliation_string":"Department of Nano-Chemical, Biological and Environmental Engineering, Seokyeong University, Seoul, Seongbuk, Republic of Korea","institution_ids":["https://openalex.org/I55188197"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077377669","display_name":"Seungyong Han","orcid":"https://orcid.org/0000-0003-2870-4088"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungyong Han","raw_affiliation_strings":["Department of Mechanical Engineering, Multiscale Bio-Inspired Technology Laboratory, Ajou University, Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-2870-4088","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Multiscale Bio-Inspired Technology Laboratory, Ajou University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044402664","display_name":"Je\u2010Sung Koh","orcid":"https://orcid.org/0000-0002-7739-0882"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Je-Sung Koh","raw_affiliation_strings":["Department of Mechanical Engineering, Multiscale Bio-Inspired Technology Laboratory, Ajou University, Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-7739-0882","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Multiscale Bio-Inspired Technology Laboratory, Ajou University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067681407","display_name":"Daeshik Kang","orcid":"https://orcid.org/0000-0002-7490-9079"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daeshik Kang","raw_affiliation_strings":["Department of Mechanical Engineering, Multiscale Bio-Inspired Technology Laboratory, Ajou University, Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-7490-9079","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Multiscale Bio-Inspired Technology Laboratory, Ajou University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I57664883"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.859,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73221033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"11","issue":null,"first_page":"95195","last_page":"95200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10504","display_name":"Sensorless Control of Electric Motors","score":0.9894999861717224,"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"}},"topics":[{"id":"https://openalex.org/T10504","display_name":"Sensorless Control of Electric Motors","score":0.9894999861717224,"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"}},{"id":"https://openalex.org/T11081","display_name":"Advanced Control Systems Design","score":0.9882000088691711,"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/T13344","display_name":"Industrial Automation and Control Systems","score":0.9639000296592712,"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/furuta-pendulum","display_name":"Furuta pendulum","score":0.885042667388916},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7332080602645874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6549884676933289},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.44507938623428345},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4328899085521698},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.38196176290512085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31834709644317627},{"id":"https://openalex.org/keywords/double-pendulum","display_name":"Double pendulum","score":0.2856842279434204}],"concepts":[{"id":"https://openalex.org/C191601290","wikidata":"https://www.wikidata.org/wiki/Q5509824","display_name":"Furuta pendulum","level":5,"score":0.885042667388916},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7332080602645874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6549884676933289},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.44507938623428345},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4328899085521698},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.38196176290512085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31834709644317627},{"id":"https://openalex.org/C167183279","wikidata":"https://www.wikidata.org/wiki/Q1243208","display_name":"Double pendulum","level":4,"score":0.2856842279434204},{"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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3310405","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3310405","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10234431.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c245d9e28a4048cbac96e5eb5b2bdd9f","is_oa":true,"landing_page_url":"https://doaj.org/article/c245d9e28a4048cbac96e5eb5b2bdd9f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 95195-95200 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3310405","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3310405","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10234431.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3966393694","display_name":null,"funder_award_id":"2022R1A2C2093100","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G4987580579","display_name":null,"funder_award_id":"2021003330009","funder_id":"https://openalex.org/F4320322007","funder_display_name":"Ministry of Environment"},{"id":"https://openalex.org/G7159020660","display_name":null,"funder_award_id":"2022R1A2C2093100","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8891062543","display_name":null,"funder_award_id":"2021003330009","funder_id":"https://openalex.org/F4320334877","funder_display_name":"Korea Environmental Industry and Technology Institute"}],"funders":[{"id":"https://openalex.org/F4320310256","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321289","display_name":"Seokyeong University","ror":"https://ror.org/04x0k0m51"},{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320321354","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73"},{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"},{"id":"https://openalex.org/F4320322007","display_name":"Ministry of Environment","ror":"https://ror.org/04xmt0833"},{"id":"https://openalex.org/F4320322073","display_name":"Korea Environment Institute","ror":"https://ror.org/00bxeqa64"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320324161","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320334877","display_name":"Korea Environmental Industry and Technology Institute","ror":"https://ror.org/022r1q746"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386275633.pdf","grobid_xml":"https://content.openalex.org/works/W4386275633.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W263701976","https://openalex.org/W1977160165","https://openalex.org/W1989276044","https://openalex.org/W1998412260","https://openalex.org/W2019820755","https://openalex.org/W2135637601","https://openalex.org/W2142787665","https://openalex.org/W2781726626","https://openalex.org/W2883338609","https://openalex.org/W2889987506","https://openalex.org/W2911087563","https://openalex.org/W2921254774","https://openalex.org/W2968116426","https://openalex.org/W2998838632","https://openalex.org/W3019560754","https://openalex.org/W4228999655","https://openalex.org/W4292408404","https://openalex.org/W4377822336","https://openalex.org/W6609718115","https://openalex.org/W6747473740","https://openalex.org/W6753526802","https://openalex.org/W6772542578"],"related_works":["https://openalex.org/W2072662323","https://openalex.org/W3216306759","https://openalex.org/W2655681456","https://openalex.org/W1994259330","https://openalex.org/W1999268506","https://openalex.org/W2082674070","https://openalex.org/W2079523531","https://openalex.org/W2380798744","https://openalex.org/W3017318039","https://openalex.org/W2967919033"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,80],"does":[2],"not":[3],"require":[4],"explicit":[5],"robot":[6],"modeling":[7],"as":[8],"it":[9,18,26,112,164],"learns":[10],"on":[11,15],"its":[12],"own":[13],"based":[14],"data,":[16],"but":[17],"is":[19,41,59,131,150],"temporal":[20,74],"and":[21,50,75,95,118,134],"spatial":[22,76],"constraints":[23],"when":[24],"transfer":[25,51],"to":[27,43,52,100,113,165],"real-world":[28],"environments.":[29],"In":[30],"this":[31,160],"research,":[32],"we":[33,86,155],"train":[34],"a":[35,46,68,82,88,142],"balancing":[36,55],"Furuta":[37,56],"pendulum":[38,57],"problem,":[39],"which":[40],"difficult":[42],"modeling,":[44],"in":[45,81,146],"virtual":[47,83,148],"environment":[48,149],"(Unity)":[49],"real-world.":[53],"The":[54,123],"problem":[58],"maintaining":[60],"balance":[61],"of":[62,159],"the":[63,73,147,157,166],"pendulum\u2019s":[64],"end":[65],"effector":[66],"at":[67],"vertical":[69],"position.":[70],"We":[71,105],"resolved":[72],"by":[77,110,162],"performing":[78],"reinforcement":[79],"environment.":[84,168],"Furthermore,":[85],"design":[87],"novel":[89],"reward":[90,103,108,129,144],"function":[91,109,130,145],"that":[92,127],"enabled":[93],"faster":[94,133],"more":[96,135],"stable":[97],"problem-solving":[98],"compared":[99],"existing":[101],"two":[102],"functions.":[104],"validate":[106],"each":[107],"applying":[111],"soft":[114],"actor":[115],"critic":[116],"(SAC)":[117],"proximal":[119],"policy":[120],"optimization":[121],"(PPO).":[122],"experimental":[124],"result":[125],"shows":[126],"cosine":[128,143],"trained":[132],"stable.":[136],"Finally,":[137],"SAC":[138],"algorithm":[139],"model":[140,161],"using":[141],"an":[151],"optimized":[152],"controller.":[153],"Additionally,":[154],"evaluated":[156],"robustness":[158],"transferring":[163],"real":[167]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
