{"id":"https://openalex.org/W4205981124","doi":"https://doi.org/10.1109/tnnls.2021.3137548","title":"Reinforcement Learning-Based Model-Free Controller for Feedback Stabilization of Robotic Systems","display_name":"Reinforcement Learning-Based Model-Free Controller for Feedback Stabilization of Robotic Systems","publication_year":2022,"publication_date":"2022-01-11","ids":{"openalex":"https://openalex.org/W4205981124","doi":"https://doi.org/10.1109/tnnls.2021.3137548","pmid":"https://pubmed.ncbi.nlm.nih.gov/35015649"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3137548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3137548","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5055996071","display_name":"Rupam Singh","orcid":"https://orcid.org/0000-0002-4494-1609"},"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":"Rupam Singh","raw_affiliation_strings":["Department of Electrical Engineering, Delhi Technological University, New Delhi, India"],"raw_orcid":"https://orcid.org/0000-0002-4494-1609","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Delhi Technological University, New Delhi, India","institution_ids":["https://openalex.org/I863896202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031425996","display_name":"Bharat Bhushan","orcid":"https://orcid.org/0000-0001-5015-4575"},"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":"Bharat Bhushan","raw_affiliation_strings":["Department of Electrical Engineering, Delhi Technological University, New Delhi, India"],"raw_orcid":"https://orcid.org/0000-0001-5015-4575","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Delhi Technological University, New Delhi, India","institution_ids":["https://openalex.org/I863896202"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I863896202"],"apc_list":null,"apc_paid":null,"fwci":1.7242,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85645205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"34","issue":"10","first_page":"7059","last_page":"7073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9987000226974487,"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":0.9987000226974487,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9976000189781189,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.992900013923645,"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":0.8730382323265076},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.735841691493988},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7310308218002319},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.6889868974685669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6126267910003662},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5660700798034668},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.46421530842781067},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.42836907505989075},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.28049665689468384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25916242599487305},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20323258638381958}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8730382323265076},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.735841691493988},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7310308218002319},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.6889868974685669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6126267910003662},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5660700798034668},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.46421530842781067},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.42836907505989075},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28049665689468384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25916242599487305},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20323258638381958},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3137548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3137548","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:35015649","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35015649","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W6614468","https://openalex.org/W1480398149","https://openalex.org/W1565170927","https://openalex.org/W1680219837","https://openalex.org/W1974386380","https://openalex.org/W1991927580","https://openalex.org/W1996340840","https://openalex.org/W2005057587","https://openalex.org/W2013216280","https://openalex.org/W2015051585","https://openalex.org/W2039876715","https://openalex.org/W2041176007","https://openalex.org/W2050214869","https://openalex.org/W2055501135","https://openalex.org/W2062420478","https://openalex.org/W2072931156","https://openalex.org/W2098432798","https://openalex.org/W2104753538","https://openalex.org/W2110040537","https://openalex.org/W2121832485","https://openalex.org/W2130599357","https://openalex.org/W2139418546","https://openalex.org/W2166706085","https://openalex.org/W2169982856","https://openalex.org/W2172291674","https://openalex.org/W2275025194","https://openalex.org/W2334750579","https://openalex.org/W2342962802","https://openalex.org/W2522467183","https://openalex.org/W2588436768","https://openalex.org/W2733312032","https://openalex.org/W2738499215","https://openalex.org/W2803973384","https://openalex.org/W2850875954","https://openalex.org/W2884086177","https://openalex.org/W2886474253","https://openalex.org/W2892258706","https://openalex.org/W2897032879","https://openalex.org/W2897039614","https://openalex.org/W2897673399","https://openalex.org/W2904304778","https://openalex.org/W2906148830","https://openalex.org/W2907944110","https://openalex.org/W2910912045","https://openalex.org/W2914358862","https://openalex.org/W2921889099","https://openalex.org/W2942307437","https://openalex.org/W2955087651","https://openalex.org/W2963017537","https://openalex.org/W2963412706","https://openalex.org/W2963576857","https://openalex.org/W2963681938","https://openalex.org/W2978626209","https://openalex.org/W3003040443","https://openalex.org/W3005243570","https://openalex.org/W3011016396","https://openalex.org/W3023512840","https://openalex.org/W3103635569","https://openalex.org/W3119113223","https://openalex.org/W3126740933","https://openalex.org/W4206333827","https://openalex.org/W4254644094","https://openalex.org/W4254952317","https://openalex.org/W4288598445","https://openalex.org/W4288614813","https://openalex.org/W4295113716","https://openalex.org/W6600262833","https://openalex.org/W6678518843","https://openalex.org/W6679630895","https://openalex.org/W6733579324","https://openalex.org/W6748537339","https://openalex.org/W6748929038","https://openalex.org/W6751694215","https://openalex.org/W6754297394","https://openalex.org/W6756870468","https://openalex.org/W6758646351","https://openalex.org/W6790301056"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W4323768008","https://openalex.org/W3131574667","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2018658498"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"a":[3,30,42,82],"reinforcement":[4],"learning":[5,26,63,79],"(RL)":[6],"algorithm":[7],"for":[8,58,81,109],"achieving":[9,122],"model-free":[10,31],"control":[11,98],"of":[12,68,77,89,100,117],"robotic":[13,105],"applications.":[14],"The":[15,45,112],"RL":[16],"functions":[17,80],"are":[18,107],"adapted":[19,52],"with":[20],"the":[21,55,62,66,75,78,87,90,93,115,118],"least-square":[22,47],"temporal":[23],"difference":[24],"(LSTD)":[25],"algorithms":[27],"to":[28,53],"develop":[29],"state":[32],"feedback":[33,83],"controller":[34],"by":[35,61],"establishing":[36],"linear":[37],"quadratic":[38],"regulator":[39],"(LQR)":[40],"as":[41],"baseline":[43],"controller.":[44],"classical":[46],"policy":[48,72],"iteration":[49],"technique":[50],"is":[51],"establish":[54],"boundary":[56],"conditions":[57],"complexities":[59],"incurred":[60],"algorithm.":[64],"Furthermore,":[65],"use":[67],"exact":[69],"and":[70,96,103,125],"approximate":[71],"iterations":[73],"estimates":[74],"parameters":[76],"policy.":[84],"To":[85],"assess":[86],"operation":[88],"proposed":[91,119],"controller,":[92],"trajectory":[94,123],"tracking":[95,124],"balancing":[97,126],"problems":[99],"unmanned":[101],"helicopters":[102],"balancer":[104],"applications":[106],"solved":[108],"real-time":[110],"experiment.":[111],"results":[113],"showed":[114],"robustness":[116],"approach":[120],"in":[121],"control.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}