{"id":"https://openalex.org/W7147157292","doi":"https://doi.org/10.1109/cnml68938.2026.11452360","title":"A Reinforcement Learning Control Strategy for Non-affine Systems","display_name":"A Reinforcement Learning Control Strategy for Non-affine Systems","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7147157292","doi":"https://doi.org/10.1109/cnml68938.2026.11452360"},"language":null,"primary_location":{"id":"doi:10.1109/cnml68938.2026.11452360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11452360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","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/A5132548646","display_name":"Xinran Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I207528943","display_name":"Chengdu Medical College","ror":"https://ror.org/01c4jmp52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I207528943"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinran Liu","raw_affiliation_strings":["Chengdu Jincheng College,Department of Intelligent Manuagacting,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"Chengdu Jincheng College,Department of Intelligent Manuagacting,Chengdu,China","institution_ids":["https://openalex.org/I207528943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5132548646"],"corresponding_institution_ids":["https://openalex.org/I207528943"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93126902,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1017","last_page":"1020"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9333000183105469,"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":0.9333000183105469,"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":0.01140000019222498,"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/T14413","display_name":"Advanced Technologies in Various Fields","score":0.006399999838322401,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/backstepping","display_name":"Backstepping","score":0.8102999925613403},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.753000020980835},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7462999820709229},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.545199990272522},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5188999772071838},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.51419997215271},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4884999990463257},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.460999995470047}],"concepts":[{"id":"https://openalex.org/C72218879","wikidata":"https://www.wikidata.org/wiki/Q4839759","display_name":"Backstepping","level":4,"score":0.8102999925613403},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.753000020980835},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7462999820709229},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.545199990272522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5242000222206116},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5188999772071838},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.51419997215271},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.44200000166893005},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4357999861240387},{"id":"https://openalex.org/C2776829284","wikidata":"https://www.wikidata.org/wiki/Q1341651","display_name":"Lyapunov stability","level":3,"score":0.4246000051498413},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.364300012588501},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2971999943256378},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C2777601987","wikidata":"https://www.wikidata.org/wiki/Q5283581","display_name":"Disturbance (geology)","level":2,"score":0.2606000006198883}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cnml68938.2026.11452360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11452360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","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/W4386883488","https://openalex.org/W4391621231","https://openalex.org/W4392979603","https://openalex.org/W4394862794","https://openalex.org/W4407948365","https://openalex.org/W4411194169","https://openalex.org/W4412939408","https://openalex.org/W4413293628","https://openalex.org/W4414501645","https://openalex.org/W4414943480","https://openalex.org/W4415053414","https://openalex.org/W4416094686","https://openalex.org/W4416515837","https://openalex.org/W4416571715","https://openalex.org/W7083580065"],"related_works":[],"abstract_inverted_index":{"To":[0],"address":[1],"the":[2,32,40,45,65,76,106,112,119,124],"challenges":[3],"of":[4,78,123],"modeling":[5],"uncertainties":[6],"and":[7,59,88,111,121],"mismatched":[8,79],"disturbances":[9],"in":[10,64,105],"non-affine":[11,46],"nonlinear":[12],"systems,":[13],"a":[14,51,69],"reinforcement":[15,52,84],"learning-based":[16],"adaptive":[17,89,94],"tracking":[18,113],"control":[19],"method":[20],"is":[21,28,55,72,96],"proposed.":[22],"First,":[23],"an":[24,36,92],"auxiliary":[25],"integral":[26],"system":[27,34,66,108],"constructed":[29],"to":[30,57,74],"transform":[31],"original":[33],"into":[35],"affine":[37],"form,":[38],"overcoming":[39],"design":[41],"difficulties":[42],"posed":[43],"by":[44,82],"structure.":[47],"On":[48],"this":[49],"basis,":[50],"learning":[53],"network":[54],"introduced":[56],"estimate":[58],"compensate":[60],"for":[61],"uncertain":[62],"nonlinearities":[63],"online,":[67],"while":[68],"disturbance":[70,86],"estimator":[71],"integrated":[73],"suppress":[75],"effects":[77],"disturbances.":[80],"Furthermore,":[81],"combining":[83],"learning,":[85],"estimation,":[87],"backstepping":[90],"control,":[91],"intelligent":[93],"controller":[95],"designed.":[97],"Lyapunov":[98],"stability":[99],"analysis":[100],"demonstrates":[101],"that":[102],"all":[103],"signals":[104],"closed-loop":[107],"are":[109],"bounded":[110],"error":[114],"converges.":[115],"Numerical":[116],"simulations":[117],"verify":[118],"effectiveness":[120],"superiority":[122],"proposed":[125],"method.":[126]},"counts_by_year":[],"updated_date":"2026-04-02T13:53:19.096889","created_date":"2026-04-02T00:00:00"}