{"id":"https://openalex.org/W3089612974","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207641","title":"Design of a Reinforcement Learning PID controller","display_name":"Design of a Reinforcement Learning PID controller","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3089612974","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207641","mag":"3089612974"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/A5071336227","display_name":"Zhe Guan","orcid":"https://orcid.org/0000-0001-6554-4242"},"institutions":[{"id":"https://openalex.org/I4210146650","display_name":"Kobelco Construction Machinery (Japan)","ror":"https://ror.org/04a307s36","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210146650"]},{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Zhe Guan","raw_affiliation_strings":["KOBELCO Construction Machinery, Hiroshima University, Higashi-Hiroshima, Japan"],"affiliations":[{"raw_affiliation_string":"KOBELCO Construction Machinery, Hiroshima University, Higashi-Hiroshima, Japan","institution_ids":["https://openalex.org/I4210146650","https://openalex.org/I113306721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070300491","display_name":"Toru Yamamoto","orcid":"https://orcid.org/0000-0001-6500-8394"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Yamamoto","raw_affiliation_strings":["Graduate School of Advanced Science and Engineering, Hiroshima University, Higashi-Hiroshima, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Engineering, Hiroshima University, Higashi-Hiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071336227"],"corresponding_institution_ids":["https://openalex.org/I113306721","https://openalex.org/I4210146650"],"apc_list":null,"apc_paid":null,"fwci":1.6886,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.87986935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"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":0.9995999932289124,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9839000105857849,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9649999737739563,"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/pid-controller","display_name":"PID controller","score":0.816022515296936},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.763920783996582},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7520883083343506},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6355882883071899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6154989004135132},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5990437865257263},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5318263173103333},{"id":"https://openalex.org/keywords/radial-basis-function","display_name":"Radial basis function","score":0.5201647281646729},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.45436954498291016},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44575217366218567},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4106164276599884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25490742921829224},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.22330525517463684},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.16010335087776184},{"id":"https://openalex.org/keywords/temperature-control","display_name":"Temperature control","score":0.11914902925491333},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11782625317573547}],"concepts":[{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.816022515296936},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.763920783996582},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7520883083343506},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6355882883071899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6154989004135132},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5990437865257263},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5318263173103333},{"id":"https://openalex.org/C98856871","wikidata":"https://www.wikidata.org/wiki/Q1588488","display_name":"Radial basis function","level":3,"score":0.5201647281646729},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.45436954498291016},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44575217366218567},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4106164276599884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25490742921829224},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.22330525517463684},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.16010335087776184},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.11914902925491333},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11782625317573547},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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":31,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1506806321","https://openalex.org/W1890078218","https://openalex.org/W1963780181","https://openalex.org/W1973538511","https://openalex.org/W1989099984","https://openalex.org/W2008663242","https://openalex.org/W2043885766","https://openalex.org/W2049857321","https://openalex.org/W2091565802","https://openalex.org/W2106504576","https://openalex.org/W2111114236","https://openalex.org/W2121863487","https://openalex.org/W2124280092","https://openalex.org/W2135637601","https://openalex.org/W2138484437","https://openalex.org/W2141185589","https://openalex.org/W2160010604","https://openalex.org/W2165726932","https://openalex.org/W2283952362","https://openalex.org/W2559850580","https://openalex.org/W2800788679","https://openalex.org/W2801182767","https://openalex.org/W2885282028","https://openalex.org/W2896122361","https://openalex.org/W2962853428","https://openalex.org/W2979268364","https://openalex.org/W2980070341","https://openalex.org/W6639847202","https://openalex.org/W6666877243","https://openalex.org/W6768850549"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370","https://openalex.org/W2152445738","https://openalex.org/W3038962357"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"a":[3,7,46],"design":[4,27],"problem":[5],"of":[6,61,67,78,86,95,183],"Proportional-Integral-Derivative":[8],"(PID)":[9],"controller":[10,74],"with":[11],"new":[12,26],"adaptive":[13,166],"updating":[14,148],"rule":[15],"based":[16,140],"on":[17,141],"Reinforcement":[18],"Learning":[19],"(RL)":[20],"approach":[21],"for":[22],"nonlinear":[23,175],"systems.":[24],"A":[25],"scheme":[28],"that":[29],"RL":[30],"can":[31,150,161],"be":[32,151,162],"used":[33],"to":[34,55,71,177],"complement":[35],"the":[36,57,64,72,76,84,91,117,124,131,147,154,158,169,179,184],"conventional":[37],"control":[38,58],"technology":[39],"PID":[40,73],"is":[41,53,112,121,138],"presented.":[42],"In":[43],"this":[44,110],"study,":[45],"single":[47],"Radial":[48],"Basis":[49],"Function":[50],"(RBF)":[51],"network":[52,80,155],"introduced":[54],"calculate":[56],"policy":[59],"function":[60,66,160],"Actor":[62],"and":[63,97,115,130,157,181],"value":[65],"Critic":[68],"simultaneously.":[69],"Regarding":[70],"structure,":[75],"inputs":[77],"RBF":[79],"are":[81,99,172],"system":[82,102],"error,":[83],"difference":[85,94,125],"output":[87],"as":[88,90,101],"well":[89],"second":[92],"order":[93],"output,":[96],"they":[98],"defined":[100,114,122],"states.":[103],"The":[104,134],"Temporal":[105],"Difference":[106],"(TD)":[107],"error":[108,118,143],"in":[109,164,174],"study":[111],"newly":[113],"involves":[116],"criterion":[119],"which":[120],"by":[123],"between":[126],"one-step":[127],"ahead":[128],"prediction":[129],"reference":[132],"value.":[133],"gradient":[135],"descent":[136],"method":[137],"adopted":[139],"TD":[142],"performance":[144],"index,":[145],"then":[146],"rules":[149],"obtained.":[152],"Therefore,":[153],"weights":[156],"kernel":[159],"calculated":[163],"an":[165],"manner.":[167],"Finally,":[168],"numerical":[170],"simulations":[171],"conducted":[173],"systems":[176],"illustrate":[178],"efficiency":[180],"robustness":[182],"proposed":[185],"scheme.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}