{"id":"https://openalex.org/W2168371024","doi":"https://doi.org/10.1109/isie.2012.6237275","title":"Model reference output feedback control using episodic natural actor-critic","display_name":"Model reference output feedback control using episodic natural actor-critic","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W2168371024","doi":"https://doi.org/10.1109/isie.2012.6237275","mag":"2168371024"},"language":"en","primary_location":{"id":"doi:10.1109/isie.2012.6237275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isie.2012.6237275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Symposium on Industrial Electronics","raw_type":"proceedings-article"},"type":"conference-paper","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/A5048127669","display_name":"Zhou Fang","orcid":"https://orcid.org/0000-0002-5389-6694"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou Fang","raw_affiliation_strings":["School of Aeronautics and Astronautics, University of Zhejiang, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, University of Zhejiang, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112839040","display_name":"Chuanchuan Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanchuan Hao","raw_affiliation_strings":["Institute of Industrial Process Control, University of Zhejiang, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Industrial Process Control, University of Zhejiang, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741314","display_name":"Li Ping","orcid":"https://orcid.org/0000-0002-4933-5093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Li","raw_affiliation_strings":["School of Aeronautics and Astronautics, University of Zhejiang, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, University of Zhejiang, Hangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":null,"first_page":"1286","last_page":"1290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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":1.0,"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":0.9980000257492065,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9850000143051147,"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/observability","display_name":"Observability","score":0.7722297310829163},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7046532034873962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6534500122070312},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.644093930721283},{"id":"https://openalex.org/keywords/output-feedback","display_name":"Output feedback","score":0.5602131485939026},{"id":"https://openalex.org/keywords/feedback-loop","display_name":"Feedback loop","score":0.4964058995246887},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4917488396167755},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4900032579898834},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4804691672325134},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.436110258102417},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.33453044295310974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2450561225414276},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20492598414421082},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17149221897125244},{"id":"https://openalex.org/keywords/temperature-control","display_name":"Temperature control","score":0.09335219860076904}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.7722297310829163},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7046532034873962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6534500122070312},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.644093930721283},{"id":"https://openalex.org/C3018623182","wikidata":"https://www.wikidata.org/wiki/Q154021","display_name":"Output feedback","level":3,"score":0.5602131485939026},{"id":"https://openalex.org/C186886427","wikidata":"https://www.wikidata.org/wiki/Q5441213","display_name":"Feedback loop","level":2,"score":0.4964058995246887},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4917488396167755},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4900032579898834},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4804691672325134},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.436110258102417},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.33453044295310974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2450561225414276},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20492598414421082},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17149221897125244},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.09335219860076904},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isie.2012.6237275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isie.2012.6237275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Symposium on Industrial Electronics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7599999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1973447767","https://openalex.org/W1988526405","https://openalex.org/W2011457905","https://openalex.org/W2094387729","https://openalex.org/W2107858701","https://openalex.org/W2125720852","https://openalex.org/W2165726932","https://openalex.org/W2172968643","https://openalex.org/W2262174858","https://openalex.org/W2374006655","https://openalex.org/W2392437395","https://openalex.org/W6992807117"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2967463586","https://openalex.org/W2765830098","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W4206221578","https://openalex.org/W3029572990","https://openalex.org/W2098619722"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"develop":[4],"a":[5,84,89],"novel":[6],"reinforcement":[7],"learning":[8],"algorithm":[9,76],"which":[10,45],"requires":[11],"only":[12],"system":[13,87],"output":[14,20,55],"and":[15,88],"converges":[16],"to":[17,38,65],"an":[18],"optimal":[19],"feedback":[21,56],"control":[22,57],"policy":[23,58,80],"with":[24],"expected":[25],"dynamic":[26],"performance.":[27],"An":[28],"informative":[29],"reward":[30,51],"function":[31],"based":[32,59],"on":[33,60,83],"reference":[34],"model":[35,92],"is":[36,63,77],"adopted":[37],"intuitively":[39],"represent":[40],"the":[41,48,67,98,101],"desired":[42],"closed-loop":[43],"performance,":[44],"significantly":[46],"reduces":[47],"difficulty":[49],"of":[50,93,100],"construction.":[52],"A":[53],"stochastic":[54],"PID":[61],"law":[62],"used":[64,78],"release":[66],"complete":[68],"observability":[69],"requirement.":[70],"The":[71],"episodic":[72],"Natural":[73],"Actor-Critic":[74],"(eNAC)":[75],"for":[79],"search.":[81],"Simulations":[82],"second-order":[85],"unstable":[86],"nonlinear":[90],"LPV":[91],"UAV's":[94],"longitudinal":[95],"dynamics":[96],"demonstrate":[97],"efficiency":[99],"proposed":[102],"algorithm.":[103]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
