{"id":"https://openalex.org/W4388937744","doi":"https://doi.org/10.1109/icccnt56998.2023.10308258","title":"Reinforcement Learning Based Controllers for Dynamical Systems","display_name":"Reinforcement Learning Based Controllers for Dynamical Systems","publication_year":2023,"publication_date":"2023-07-06","ids":{"openalex":"https://openalex.org/W4388937744","doi":"https://doi.org/10.1109/icccnt56998.2023.10308258"},"language":"en","primary_location":{"id":"doi:10.1109/icccnt56998.2023.10308258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt56998.2023.10308258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)","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/A5068390815","display_name":"Mallika Singh","orcid":"https://orcid.org/0000-0002-2640-7592"},"institutions":[{"id":"https://openalex.org/I863896202","display_name":"Delhi Technological University","ror":"https://ror.org/01ztcvt22","country_code":"IN","type":"education","lineage":["https://openalex.org/I863896202"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Mallika Singh","raw_affiliation_strings":["Delhi Technological University,Department of Electrical Engineering,New Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delhi Technological University,Department of Electrical Engineering,New Delhi,India","institution_ids":["https://openalex.org/I863896202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068713578","display_name":"Madan Mohan Rayguru","orcid":"https://orcid.org/0000-0003-4339-4444"},"institutions":[{"id":"https://openalex.org/I863896202","display_name":"Delhi Technological University","ror":"https://ror.org/01ztcvt22","country_code":"IN","type":"education","lineage":["https://openalex.org/I863896202"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Madan Mohan Rayguru","raw_affiliation_strings":["Delhi Technological University,Department of Electrical Engineering,New Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delhi Technological University,Department of Electrical Engineering,New Delhi,India","institution_ids":["https://openalex.org/I863896202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021261194","display_name":"Gaurav Kaushik","orcid":"https://orcid.org/0000-0001-6743-7811"},"institutions":[{"id":"https://openalex.org/I863896202","display_name":"Delhi Technological University","ror":"https://ror.org/01ztcvt22","country_code":"IN","type":"education","lineage":["https://openalex.org/I863896202"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gaurav Kaushik","raw_affiliation_strings":["Delhi Technological University,Department of Electrical Engineering,New Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delhi Technological University,Department of Electrical Engineering,New Delhi,India","institution_ids":["https://openalex.org/I863896202"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068390815"],"corresponding_institution_ids":["https://openalex.org/I863896202"],"apc_list":null,"apc_paid":null,"fwci":0.583,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72675737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9969000220298767,"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":0.9969000220298767,"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":0.9952999949455261,"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":0.9819999933242798,"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":0.9389752149581909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6485359072685242},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6167886257171631},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.588632345199585},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5709381103515625},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5135026574134827},{"id":"https://openalex.org/keywords/dynamical-systems-theory","display_name":"Dynamical systems theory","score":0.49049681425094604},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.4568633735179901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41856369376182556},{"id":"https://openalex.org/keywords/dynamical-system","display_name":"Dynamical system (definition)","score":0.4105316996574402},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34448546171188354},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20082908868789673},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17077171802520752}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9389752149581909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6485359072685242},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6167886257171631},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.588632345199585},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5709381103515625},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5135026574134827},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.49049681425094604},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.4568633735179901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41856369376182556},{"id":"https://openalex.org/C33962884","wikidata":"https://www.wikidata.org/wiki/Q378637","display_name":"Dynamical system (definition)","level":3,"score":0.4105316996574402},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34448546171188354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20082908868789673},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17077171802520752},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccnt56998.2023.10308258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt56998.2023.10308258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)","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":15,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2035003264","https://openalex.org/W2070824031","https://openalex.org/W2096018174","https://openalex.org/W2151966330","https://openalex.org/W2170396314","https://openalex.org/W2972128755","https://openalex.org/W3022551911","https://openalex.org/W3091774741","https://openalex.org/W3118439514","https://openalex.org/W3158253560","https://openalex.org/W3169732227","https://openalex.org/W4285240592","https://openalex.org/W4289538237","https://openalex.org/W4292999311"],"related_works":["https://openalex.org/W2955790965","https://openalex.org/W4250831671","https://openalex.org/W2230606337","https://openalex.org/W2089869689","https://openalex.org/W4388681848","https://openalex.org/W2078952919","https://openalex.org/W2945666329","https://openalex.org/W2617651062","https://openalex.org/W1559871661","https://openalex.org/W2952478110"],"abstract_inverted_index":{"Designing":[0],"controllers":[1],"for":[2,72],"dynamical":[3],"system":[4,131],"poses":[5],"a":[6,42,50,119,125,130],"challenge,":[7],"as":[8,110],"besides":[9],"keeping":[10],"in":[11,35,136,147],"mind":[12],"the":[13,25,30,45,62,89,93,106,116,133,143,151,154],"changing":[14],"state":[15,73],"and":[16,78,105,122],"input":[17],"conditions,":[18],"another":[19],"secondary":[20],"objective":[21],"of":[22,44,91,118,153],"either":[23],"minimizing":[24],"cost":[26],"function":[27,127],"or":[28],"maximizing":[29],"reward":[31,126],"must":[32],"be":[33],"kept":[34],"mind.":[36],"While":[37],"most":[38],"modern":[39],"methods":[40],"require":[41],"model":[43,57],"system,":[46],"this":[47],"paper":[48,113],"proposes":[49],"reinforcement":[51,60],"learning":[52],"based":[53],"method":[54],"which":[55,95],"is":[56,70,82,96,100,157],"free.":[58],"Under":[59],"learning,":[61],"Q-learning":[63,120],"algorithm":[64,69,155],"has":[65],"been":[66],"used.":[67],"This":[68,112],"apt":[71],"spaces":[74],"with":[75,88,132],"discrete":[76,103],"states":[77,104],"actions.":[79],"Here,":[80],"Q-Learning":[81],"applied":[83],"to":[84,149],"discrete-time":[85],"linear":[86],"systems":[87],"intention":[90],"finding":[92],"policy":[94],"optimal.":[97],"The":[98,139],"environment":[99],"broken":[101],"into":[102,115],"actions":[107],"are":[108,145],"defined":[109],"well.":[111],"delves":[114],"design":[117],"framework":[121],"working":[123],"out":[124],"that":[128,156],"helps":[129],"given":[134],"dynamics":[135],"behaving":[137],"optimally.":[138],"results":[140],"obtained":[141],"from":[142],"simulation":[144],"shown":[146],"order":[148],"assess":[150],"efficacy":[152],"being":[158],"developed.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}