{"id":"https://openalex.org/W3126909900","doi":"https://doi.org/10.1109/iciis51140.2020.9342690","title":"Reinforcement learning control of servo actuated centrally pivoted ball on a beam","display_name":"Reinforcement learning control of servo actuated centrally pivoted ball on a beam","publication_year":2020,"publication_date":"2020-11-26","ids":{"openalex":"https://openalex.org/W3126909900","doi":"https://doi.org/10.1109/iciis51140.2020.9342690","mag":"3126909900"},"language":"en","primary_location":{"id":"doi:10.1109/iciis51140.2020.9342690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iciis51140.2020.9342690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS)","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/A5025717019","display_name":"Archana Ganesh","orcid":"https://orcid.org/0000-0003-0595-0956"},"institutions":[{"id":"https://openalex.org/I122964287","display_name":"National Institute of Technology Tiruchirappalli","ror":"https://ror.org/047x65e68","country_code":"IN","type":"education","lineage":["https://openalex.org/I122964287"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Archana Ganesh","raw_affiliation_strings":["National Institute of Technology,Dept. of Instrumentation and Control,Tiruchirappalli,India","Dept. of Instrumentation and Control, National Institute of Technology, Tiruchirappalli, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology,Dept. of Instrumentation and Control,Tiruchirappalli,India","institution_ids":["https://openalex.org/I122964287"]},{"raw_affiliation_string":"Dept. of Instrumentation and Control, National Institute of Technology, Tiruchirappalli, India","institution_ids":["https://openalex.org/I122964287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066032118","display_name":"M. Banu Sundareswari","orcid":null},"institutions":[{"id":"https://openalex.org/I122964287","display_name":"National Institute of Technology Tiruchirappalli","ror":"https://ror.org/047x65e68","country_code":"IN","type":"education","lineage":["https://openalex.org/I122964287"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"M. Banu Sundareswari","raw_affiliation_strings":["National Institute of Technology,Dept. of Instrumentation and Control,Tiruchirappalli,India","Dept. of Instrumentation and Control, National Institute of Technology, Tiruchirappalli, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology,Dept. of Instrumentation and Control,Tiruchirappalli,India","institution_ids":["https://openalex.org/I122964287"]},{"raw_affiliation_string":"Dept. of Instrumentation and Control, National Institute of Technology, Tiruchirappalli, India","institution_ids":["https://openalex.org/I122964287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101648097","display_name":"Monalisa Panda","orcid":"https://orcid.org/0000-0002-6451-0718"},"institutions":[{"id":"https://openalex.org/I122964287","display_name":"National Institute of Technology Tiruchirappalli","ror":"https://ror.org/047x65e68","country_code":"IN","type":"education","lineage":["https://openalex.org/I122964287"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Monalisa Panda","raw_affiliation_strings":["National Institute of Technology,Dept. of Instrumentation and Control,Tiruchirappalli,India","Dept. of Instrumentation and Control, National Institute of Technology, Tiruchirappalli, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology,Dept. of Instrumentation and Control,Tiruchirappalli,India","institution_ids":["https://openalex.org/I122964287"]},{"raw_affiliation_string":"Dept. of Instrumentation and Control, National Institute of Technology, Tiruchirappalli, India","institution_ids":["https://openalex.org/I122964287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028616472","display_name":"G Then Mozhi","orcid":null},"institutions":[{"id":"https://openalex.org/I122964287","display_name":"National Institute of Technology Tiruchirappalli","ror":"https://ror.org/047x65e68","country_code":"IN","type":"education","lineage":["https://openalex.org/I122964287"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"G Then Mozhi","raw_affiliation_strings":["National Institute of Technology,Dept. of Instrumentation and Control,Tiruchirappalli,India","Dept. of Instrumentation and Control, National Institute of Technology, Tiruchirappalli, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology,Dept. of Instrumentation and Control,Tiruchirappalli,India","institution_ids":["https://openalex.org/I122964287"]},{"raw_affiliation_string":"Dept. of Instrumentation and Control, National Institute of Technology, Tiruchirappalli, India","institution_ids":["https://openalex.org/I122964287"]}]},{"author_position":"last","author":{"id":null,"display_name":"K Dhanalakshmi","orcid":null},"institutions":[{"id":"https://openalex.org/I122964287","display_name":"National Institute of Technology Tiruchirappalli","ror":"https://ror.org/047x65e68","country_code":"IN","type":"education","lineage":["https://openalex.org/I122964287"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K Dhanalakshmi","raw_affiliation_strings":["National Institute of Technology,Dept. of Instrumentation and Control,Tiruchirappalli,India","Dept. of Instrumentation and Control, National Institute of Technology, Tiruchirappalli, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology,Dept. of Instrumentation and Control,Tiruchirappalli,India","institution_ids":["https://openalex.org/I122964287"]},{"raw_affiliation_string":"Dept. of Instrumentation and Control, National Institute of Technology, Tiruchirappalli, India","institution_ids":["https://openalex.org/I122964287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I122964287"],"apc_list":null,"apc_paid":null,"fwci":0.1457,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57405495,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"103","last_page":"108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9703999757766724,"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":0.9703999757766724,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.968500018119812,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9639000296592712,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9285556077957153},{"id":"https://openalex.org/keywords/setpoint","display_name":"Setpoint","score":0.821071982383728},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6590214371681213},{"id":"https://openalex.org/keywords/ball","display_name":"Ball (mathematics)","score":0.5973835587501526},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5698830485343933},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5423290729522705},{"id":"https://openalex.org/keywords/servomotor","display_name":"Servomotor","score":0.5129725337028503},{"id":"https://openalex.org/keywords/servomechanism","display_name":"Servomechanism","score":0.5070657730102539},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4715787470340729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4234932065010071},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3079932630062103},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2449241578578949},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20516571402549744},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.13850316405296326}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9285556077957153},{"id":"https://openalex.org/C12302492","wikidata":"https://www.wikidata.org/wiki/Q1752097","display_name":"Setpoint","level":2,"score":0.821071982383728},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6590214371681213},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.5973835587501526},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5698830485343933},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5423290729522705},{"id":"https://openalex.org/C109441226","wikidata":"https://www.wikidata.org/wiki/Q1137255","display_name":"Servomotor","level":2,"score":0.5129725337028503},{"id":"https://openalex.org/C49503481","wikidata":"https://www.wikidata.org/wiki/Q640815","display_name":"Servomechanism","level":2,"score":0.5070657730102539},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4715787470340729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4234932065010071},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3079932630062103},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2449241578578949},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20516571402549744},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.13850316405296326},{"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iciis51140.2020.9342690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iciis51140.2020.9342690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W190583841","https://openalex.org/W311853785","https://openalex.org/W2011334339","https://openalex.org/W2049816660","https://openalex.org/W2096755218","https://openalex.org/W2121863487","https://openalex.org/W2155182763","https://openalex.org/W2736601468","https://openalex.org/W2786092665","https://openalex.org/W2963864421","https://openalex.org/W6610972542","https://openalex.org/W6684921986","https://openalex.org/W6741002519"],"related_works":["https://openalex.org/W1495927848","https://openalex.org/W4205962020","https://openalex.org/W2620138946","https://openalex.org/W1527771352","https://openalex.org/W90946887","https://openalex.org/W191702426","https://openalex.org/W4255293822","https://openalex.org/W2994131054","https://openalex.org/W2115261773","https://openalex.org/W2021648837"],"abstract_inverted_index":{"The":[0,26,45,63,99,116],"objective":[1],"of":[2,88,105,121,152],"this":[3,159],"work":[4],"is":[5,31,54,61,90,102,120,166,170],"to":[6,32,41,94,110,158],"devise":[7],"a":[8,42,80,122],"controller":[9],"using":[10],"Reinforcement":[11,46,127],"Learning":[12,47,128],"(RL)":[13],"agents,":[14],"for":[15],"unstable":[16],"and":[17,69,125,139,163],"complex":[18],"control":[19],"systems":[20],"like":[21],"the":[22,34,58,70,84,96,103,106,114,126,146,153,164,173],"ball":[23,72,81],"beam":[24,107],"system.":[25],"reinforcement":[27,154],"learning":[28,155],"agent's":[29],"job":[30],"keep":[33],"ball's":[35],"position":[36,73,82],"as":[37,39,75,77,92,172],"close":[38,76],"possible":[40],"set":[43],"point.":[44],"agent":[48],"learns":[49],"through":[50],"rewards.":[51],"Every":[52],"action":[53,101,117],"taken":[55,91],"such":[56],"that":[57,130],"reward":[59,64,89],"value":[60],"maximized.":[62],"becomes":[65],"maximum":[66],"if":[67],"setpoint":[68],"current":[71],"are":[74,134,149,161],"possible.":[78],"So,":[79],"from":[83],"sensor,":[85],"in":[86],"terms":[87],"feedback":[93],"predict":[95],"next":[97],"action.":[98],"predicted":[100],"angle":[104],"which":[108],"needs":[109],"be":[111],"turned":[112],"by":[113],"motor.":[115],"space":[118],"considered":[119],"continuous":[123],"domain,":[124],"algorithms":[129,156],"have":[131],"been":[132],"used":[133,171],"Proximal":[135],"Policy":[136,142],"Optimization":[137],"(PPO)":[138],"Deep":[140],"Deterministic":[141],"Gradient":[143],"(DDPG).":[144],"Once":[145],"environment":[147,160],"dynamics":[148],"defined,":[150],"hyper-parameters":[151],"pertaining":[157],"tuned,":[162],"model":[165],"trained.":[167],"Servo":[168],"motor":[169],"actuation":[174],"mechanism.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
