{"id":"https://openalex.org/W2901974609","doi":"https://doi.org/10.1109/iceee.2018.8533946","title":"Reinforcement Learning Compensation based PD Control for Inverted Pendulum","display_name":"Reinforcement Learning Compensation based PD Control for Inverted Pendulum","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2901974609","doi":"https://doi.org/10.1109/iceee.2018.8533946","mag":"2901974609"},"language":"en","primary_location":{"id":"doi:10.1109/iceee.2018.8533946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceee.2018.8533946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 15th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE)","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/A5064145175","display_name":"Guillermo Puriel\u2010Gil","orcid":null},"institutions":[{"id":"https://openalex.org/I68368234","display_name":"Center for Research and Advanced Studies of the National Polytechnic Institute","ror":"https://ror.org/009eqmr18","country_code":"MX","type":"facility","lineage":["https://openalex.org/I59361560","https://openalex.org/I68368234"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Guillermo Puriel-Gil","raw_affiliation_strings":["Departamento de Control Autom\u00e1tico, CINVESTAV-IPN, Ciudad de M\u00e9xico, M\u00e9xico"],"affiliations":[{"raw_affiliation_string":"Departamento de Control Autom\u00e1tico, CINVESTAV-IPN, Ciudad de M\u00e9xico, M\u00e9xico","institution_ids":["https://openalex.org/I68368234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008201587","display_name":"Wen Yu","orcid":"https://orcid.org/0000-0002-9540-7924"},"institutions":[{"id":"https://openalex.org/I68368234","display_name":"Center for Research and Advanced Studies of the National Polytechnic Institute","ror":"https://ror.org/009eqmr18","country_code":"MX","type":"facility","lineage":["https://openalex.org/I59361560","https://openalex.org/I68368234"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Wen Yu","raw_affiliation_strings":["Departamento de Control Autom\u00e1tico, CINVESTAV-IPN, Ciudad de M\u00e9xico, M\u00e9xico"],"affiliations":[{"raw_affiliation_string":"Departamento de Control Autom\u00e1tico, CINVESTAV-IPN, Ciudad de M\u00e9xico, M\u00e9xico","institution_ids":["https://openalex.org/I68368234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007636051","display_name":"Humberto Sossa","orcid":"https://orcid.org/0000-0002-0521-4898"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]},{"id":"https://openalex.org/I68368234","display_name":"Center for Research and Advanced Studies of the National Polytechnic Institute","ror":"https://ror.org/009eqmr18","country_code":"MX","type":"facility","lineage":["https://openalex.org/I59361560","https://openalex.org/I68368234"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Humberto Sossa","raw_affiliation_strings":["CINVESTAV-IPN, INSTITUTO POLIT\u00c9CNICO NACIONAL, Ciudad de M\u00e9xico, M\u00e9xico"],"affiliations":[{"raw_affiliation_string":"CINVESTAV-IPN, INSTITUTO POLIT\u00c9CNICO NACIONAL, Ciudad de M\u00e9xico, M\u00e9xico","institution_ids":["https://openalex.org/I59361560","https://openalex.org/I68368234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064145175"],"corresponding_institution_ids":["https://openalex.org/I68368234"],"apc_list":null,"apc_paid":null,"fwci":1.2875,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.81791283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"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/T14011","display_name":"Elevator Systems and Control","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.9969000220298767,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9905999898910522,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9890999794006348,"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/inverted-pendulum","display_name":"Inverted pendulum","score":0.9727803468704224},{"id":"https://openalex.org/keywords/double-inverted-pendulum","display_name":"Double inverted pendulum","score":0.8187117576599121},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7595244646072388},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6767317056655884},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6049471497535706},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5911946296691895},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5896307229995728},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.5024352073669434},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4896717369556427},{"id":"https://openalex.org/keywords/pendulum","display_name":"Pendulum","score":0.4739532470703125},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.414318323135376},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.37538307905197144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28329572081565857},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.27258431911468506},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22725874185562134},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.09599500894546509},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0846967101097107}],"concepts":[{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.9727803468704224},{"id":"https://openalex.org/C102540577","wikidata":"https://www.wikidata.org/wiki/Q5300047","display_name":"Double inverted pendulum","level":4,"score":0.8187117576599121},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7595244646072388},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6767317056655884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6049471497535706},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5911946296691895},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5896307229995728},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.5024352073669434},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4896717369556427},{"id":"https://openalex.org/C110639684","wikidata":"https://www.wikidata.org/wiki/Q20702","display_name":"Pendulum","level":2,"score":0.4739532470703125},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.414318323135376},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.37538307905197144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28329572081565857},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27258431911468506},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22725874185562134},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.09599500894546509},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0846967101097107},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iceee.2018.8533946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceee.2018.8533946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 15th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321694","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34"},{"id":"https://openalex.org/F4320321739","display_name":"Consejo Nacional de Ciencia y Tecnolog\u00eda","ror":"https://ror.org/059ex5q34"},{"id":"https://openalex.org/F4320324201","display_name":"Secretar\u00eda de Investigaci\u00f3n y Posgrado, Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34"},{"id":"https://openalex.org/F4320335331","display_name":"Centro de Investigaci\u00f3n y de Estudios Avanzados del Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W109339162","https://openalex.org/W1496777766","https://openalex.org/W1567145281","https://openalex.org/W1977655452","https://openalex.org/W2012392077","https://openalex.org/W2012587148","https://openalex.org/W2067349577","https://openalex.org/W2101915445","https://openalex.org/W2103528668","https://openalex.org/W2107726111","https://openalex.org/W2113362840","https://openalex.org/W2115180116","https://openalex.org/W2115932303","https://openalex.org/W2121863487","https://openalex.org/W2124491905","https://openalex.org/W2152446322","https://openalex.org/W2157356547","https://openalex.org/W2167117957","https://openalex.org/W2236244207","https://openalex.org/W2541921436","https://openalex.org/W2580909119","https://openalex.org/W3098163860","https://openalex.org/W3123298421","https://openalex.org/W4205513846","https://openalex.org/W6604447009","https://openalex.org/W6653435097","https://openalex.org/W6784958018"],"related_works":["https://openalex.org/W2024927487","https://openalex.org/W1492838287","https://openalex.org/W2034778971","https://openalex.org/W2349578589","https://openalex.org/W2612646280","https://openalex.org/W2893549521","https://openalex.org/W2204278379","https://openalex.org/W2381121570","https://openalex.org/W2379721524","https://openalex.org/W2341932412"],"abstract_inverted_index":{"In":[0,46,66],"this":[1,80],"paper,":[2],"we":[3,70,82],"present":[4],"a":[5,47,67],"Control":[6],"Algorithm":[7],"based":[8],"on":[9],"Reinforcement":[10],"Learning":[11],"for":[12],"an":[13],"inverted":[14,63,89],"pendulum.":[15],"By":[16],"implementing":[17],"the":[18,22,26,40,43,55,59,85,94,98,101,104,107],"Q-Learning":[19,50,75],"techniques":[20,73],"in":[21,39],"PD":[23,77],"control":[24,56],"scheme,":[25],"pendulum":[27,44,60,86],"is":[28,51],"enabled":[29],"to":[30,37,87],"improve":[31],"its":[32,62,88],"online":[33],"performance":[34],"and":[35,76],"adapt":[36],"changes":[38],"parameters":[41],"of":[42,74,93,100,106],"model.":[45],"first":[48],"step,":[49,69],"used":[52],"so":[53],"that":[54],"can":[57,83],"balance":[58],"towards":[61],"vertical":[64,90],"position;":[65],"second":[68],"combine":[71],"hybrid":[72],"control.":[78],"With":[79],"combination,":[81],"bring":[84],"position,":[91],"regardless":[92],"applied":[95],"disturbance.":[96],"Finally,":[97],"results":[99],"simulation":[102],"show":[103],"effectiveness":[105],"proposed":[108],"controller.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-01-16T23:16:36.188383","created_date":"2025-10-10T00:00:00"}
