{"id":"https://openalex.org/W4389332256","doi":"https://doi.org/10.1109/cce60043.2023.10332814","title":"Stability Guaranteed Actor-Critic Learning for Robots in Continuous Time","display_name":"Stability Guaranteed Actor-Critic Learning for Robots in Continuous Time","publication_year":2023,"publication_date":"2023-10-25","ids":{"openalex":"https://openalex.org/W4389332256","doi":"https://doi.org/10.1109/cce60043.2023.10332814"},"language":"en","primary_location":{"id":"doi:10.1109/cce60043.2023.10332814","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cce60043.2023.10332814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 20th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE)","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/A5011668012","display_name":"Luis Pantoja\u2010Garcia","orcid":"https://orcid.org/0000-0002-6606-861X"},"institutions":[{"id":"https://openalex.org/I68368234","display_name":"Center for Research and Advanced Studies of the National Polytechnic Institute","ror":"https://ror.org/009eqmr18","country_code":"MX","type":"facility","lineage":["https://openalex.org/I59361560","https://openalex.org/I68368234"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Luis Pantoja-Garcia","raw_affiliation_strings":["Robotics and Adv. Manufacturing CINVESTAV,Saltillo,Mexico","Robotics and Adv. Manufacturing CINVESTAV, Saltillo, Mexico"],"affiliations":[{"raw_affiliation_string":"Robotics and Adv. Manufacturing CINVESTAV,Saltillo,Mexico","institution_ids":["https://openalex.org/I68368234"]},{"raw_affiliation_string":"Robotics and Adv. Manufacturing CINVESTAV, Saltillo, Mexico","institution_ids":["https://openalex.org/I68368234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028434777","display_name":"Vicente Parra\u2010Vega","orcid":"https://orcid.org/0000-0002-1813-0394"},"institutions":[{"id":"https://openalex.org/I68368234","display_name":"Center for Research and Advanced Studies of the National Polytechnic Institute","ror":"https://ror.org/009eqmr18","country_code":"MX","type":"facility","lineage":["https://openalex.org/I59361560","https://openalex.org/I68368234"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Vicente Parra-Vega","raw_affiliation_strings":["Robotics and Adv. Manufacturing CINVESTAV,Saltillo,Mexico","Robotics and Adv. Manufacturing CINVESTAV, Saltillo, Mexico"],"affiliations":[{"raw_affiliation_string":"Robotics and Adv. Manufacturing CINVESTAV,Saltillo,Mexico","institution_ids":["https://openalex.org/I68368234"]},{"raw_affiliation_string":"Robotics and Adv. Manufacturing CINVESTAV, Saltillo, Mexico","institution_ids":["https://openalex.org/I68368234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068596586","display_name":"Rodolfo Garc\u00eda-Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-4402-6072"},"institutions":[{"id":"https://openalex.org/I4210118275","display_name":"Universidad Polit\u00e9cnica Metropolitana de Hidalgo","ror":"https://ror.org/02ne61390","country_code":"MX","type":"education","lineage":["https://openalex.org/I4210118275"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Rodolfo Garcia-Rodriguez","raw_affiliation_strings":["Universidad Politecnica Metropolitana de Hidalgo,Postgraduate Program in Aerospacial Engineering,Tolcayuca","Postgraduate Program in Aerospacial Engineering, Universidad Politecnica Metropolitana de Hidalgo, Tolcayuca"],"affiliations":[{"raw_affiliation_string":"Universidad Politecnica Metropolitana de Hidalgo,Postgraduate Program in Aerospacial Engineering,Tolcayuca","institution_ids":["https://openalex.org/I4210118275"]},{"raw_affiliation_string":"Postgraduate Program in Aerospacial Engineering, Universidad Politecnica Metropolitana de Hidalgo, Tolcayuca","institution_ids":["https://openalex.org/I4210118275"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011668012"],"corresponding_institution_ids":["https://openalex.org/I68368234"],"apc_list":null,"apc_paid":null,"fwci":0.3978,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67235233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6843235492706299},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.646594226360321},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6111270189285278},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6035670042037964},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.541670024394989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5292930603027344},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.4616597294807434},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4568023383617401},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.41638708114624023},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.35657817125320435},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2321135699748993},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.17912650108337402},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.12332841753959656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6843235492706299},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.646594226360321},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6111270189285278},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6035670042037964},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.541670024394989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5292930603027344},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.4616597294807434},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4568023383617401},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.41638708114624023},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.35657817125320435},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2321135699748993},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.17912650108337402},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.12332841753959656},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cce60043.2023.10332814","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cce60043.2023.10332814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 20th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1517236425","https://openalex.org/W1983523797","https://openalex.org/W2015982707","https://openalex.org/W2113501460","https://openalex.org/W2122739526","https://openalex.org/W2145956080","https://openalex.org/W2964330577","https://openalex.org/W3045059767","https://openalex.org/W3114329882","https://openalex.org/W3153592393","https://openalex.org/W3155511388","https://openalex.org/W3190755268","https://openalex.org/W4214717370","https://openalex.org/W4248443165","https://openalex.org/W4282946060","https://openalex.org/W4294555834","https://openalex.org/W4309471869"],"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/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W3021988786","https://openalex.org/W3099311996","https://openalex.org/W2963971282"],"abstract_inverted_index":{"Actor-Critic":[0],"(AC)":[1],"architecture":[2],"has":[3,64],"the":[4,8,31,39,56,67,90,94,102,114,117,149,152,161,172,188,196],"salient":[5],"feature,":[6],"for":[7,127],"plethora":[9],"of":[10,89,106,113,116,151,171],"Reinforcement":[11],"Learning":[12],"schemes,":[13],"that":[14,27,98,123,132],"two":[15],"intertwining":[16],"neural":[17,118],"networks":[18],"(NN)":[19],"collaborate":[20],"to":[21,33,51,54,69,100,165],"deploy":[22],"a":[23,35,60,85,134,138,178,192],"motor":[24],"learning":[25,173,189],"mechanism":[26,97,174,190],"oversees":[28],"and":[29,187],"evaluates":[30],"action":[32,104],"control":[34,55],"dynamical":[36,49],"system":[37],"as":[38,48],"robot":[40,57,162],"manipulator.":[41],"Since":[42],"such":[43],"NNs":[44],"can":[45],"be":[46],"studied":[47],"systems":[50],"learn":[52],"how":[53],"dynamics":[58],"with":[59,71,142,182],"given":[61],"performance,":[62],"it":[63],"finally":[65],"paved":[66],"way":[68],"deal":[70],"stability":[72,122],"analysis,":[73],"unfortunately,":[74],"few":[75],"works":[76],"have":[77],"addressed":[78],"it.":[79],"In":[80,155],"this":[81],"paper,":[82],"we":[83],"propose":[84],"Critic-NN":[86],"whose":[87],"approximation":[88],"value":[91],"function":[92],"substantiates":[93],"decision":[95],"making":[96],"collaborates":[99],"tune":[101],"Actor-NN":[103],"(approximation":[105],"inverse":[107],"dynamics).":[108],"The":[109],"novel":[110],"proposed":[111,153],"design":[112],"adaptation":[115],"weights":[119],"yields":[120],"Lyapunov":[121],"provides":[124],"explicit":[125],"conditions":[126],"an":[128],"attractive":[129],"invariant":[130],"set":[131],"render":[133],"stable":[135],"regime":[136],"using":[137],"quite":[139],"simple":[140],"NN":[141],"one":[143],"hidden":[144],"layer.":[145],"Numerical":[146],"simulations":[147],"show":[148],"performance":[150],"approach.":[154],"addition,":[156],"robustness":[157,185],"is":[158,163,199],"analyzed":[159],"when":[160,175],"subject":[164],"Liptchitz":[166],"disturbances,":[167],"interestingly":[168],"showing":[169],"relaunching":[170],"needed.":[176],"Finally,":[177],"discussion":[179],"on":[180],"dealing":[181],"asymptotic":[183],"stability,":[184],"issues,":[186],"from":[191],"reward":[193],"provided":[194],"by":[195],"expert":[197],"user":[198],"addressed.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}