{"id":"https://openalex.org/W4385938123","doi":"https://doi.org/10.1109/access.2023.3306070","title":"An Actor-Critic Framework for Online Control With Environment Stability Guarantee","display_name":"An Actor-Critic Framework for Online Control With Environment Stability Guarantee","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385938123","doi":"https://doi.org/10.1109/access.2023.3306070"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3306070","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2023.3306070","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10223230.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10223230.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065280230","display_name":"Pavel Osinenko","orcid":"https://orcid.org/0000-0002-6184-3293"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Pavel Osinenko","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0002-6184-3293","affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054781489","display_name":"Grigory Yaremenko","orcid":"https://orcid.org/0000-0002-8869-6422"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Grigory Yaremenko","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0002-8869-6422","affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002667621","display_name":"Georgiy Malaniya","orcid":"https://orcid.org/0000-0002-2936-6271"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Georgiy Malaniya","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0002-2936-6271","affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008864190","display_name":"Anton Bolychev","orcid":null},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Anton Bolychev","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125989756"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.279,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57075224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"11","issue":null,"first_page":"89188","last_page":"89204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9993000030517578,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9671000242233276,"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":0.8229342103004456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7564939260482788},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.658139705657959},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5141708850860596},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4902222752571106},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4886768162250519},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.48283347487449646},{"id":"https://openalex.org/keywords/lyapunov-stability","display_name":"Lyapunov stability","score":0.44729194045066833},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.41481804847717285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4074885845184326},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22405660152435303}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8229342103004456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7564939260482788},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.658139705657959},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5141708850860596},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4902222752571106},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4886768162250519},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.48283347487449646},{"id":"https://openalex.org/C2776829284","wikidata":"https://www.wikidata.org/wiki/Q1341651","display_name":"Lyapunov stability","level":3,"score":0.44729194045066833},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.41481804847717285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4074885845184326},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22405660152435303},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3306070","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2023.3306070","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10223230.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6df1137542c64d1891565ed0d8b984da","is_oa":true,"landing_page_url":"https://doaj.org/article/6df1137542c64d1891565ed0d8b984da","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 89188-89204 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3306070","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2023.3306070","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10223230.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385938123.pdf","grobid_xml":"https://content.openalex.org/works/W4385938123.grobid-xml"},"referenced_works_count":131,"referenced_works":["https://openalex.org/W34013550","https://openalex.org/W181569489","https://openalex.org/W560518094","https://openalex.org/W1513689897","https://openalex.org/W1535116423","https://openalex.org/W1579485993","https://openalex.org/W1967178780","https://openalex.org/W1994392685","https://openalex.org/W2019671144","https://openalex.org/W2038341035","https://openalex.org/W2048687352","https://openalex.org/W2052305027","https://openalex.org/W2062915697","https://openalex.org/W2067390368","https://openalex.org/W2073591687","https://openalex.org/W2073787051","https://openalex.org/W2080209002","https://openalex.org/W2086975818","https://openalex.org/W2087617385","https://openalex.org/W2089059393","https://openalex.org/W2091985923","https://openalex.org/W2093831009","https://openalex.org/W2099767582","https://openalex.org/W2103782731","https://openalex.org/W2104843094","https://openalex.org/W2106768170","https://openalex.org/W2109102709","https://openalex.org/W2113501460","https://openalex.org/W2127107099","https://openalex.org/W2130801532","https://openalex.org/W2144446635","https://openalex.org/W2145363145","https://openalex.org/W2153039919","https://openalex.org/W2161009228","https://openalex.org/W2162053828","https://openalex.org/W2165545652","https://openalex.org/W2165726932","https://openalex.org/W2169300227","https://openalex.org/W2257979135","https://openalex.org/W2269274350","https://openalex.org/W2314983263","https://openalex.org/W2416041116","https://openalex.org/W2528489519","https://openalex.org/W2564717627","https://openalex.org/W2736629007","https://openalex.org/W2749680651","https://openalex.org/W2751786346","https://openalex.org/W2778917778","https://openalex.org/W2787908307","https://openalex.org/W2790759697","https://openalex.org/W2800330509","https://openalex.org/W2887039782","https://openalex.org/W2889731659","https://openalex.org/W2892521964","https://openalex.org/W2897283383","https://openalex.org/W2901005637","https://openalex.org/W2902624920","https://openalex.org/W2902907165","https://openalex.org/W2909414402","https://openalex.org/W2910238521","https://openalex.org/W2917945410","https://openalex.org/W2927564896","https://openalex.org/W2942027162","https://openalex.org/W2948652605","https://openalex.org/W2949510088","https://openalex.org/W2963355572","https://openalex.org/W2966735560","https://openalex.org/W2968788589","https://openalex.org/W2970161765","https://openalex.org/W2971484784","https://openalex.org/W2980297602","https://openalex.org/W2982316857","https://openalex.org/W2992608041","https://openalex.org/W2995298643","https://openalex.org/W2995484204","https://openalex.org/W2998461398","https://openalex.org/W2998959212","https://openalex.org/W3000437856","https://openalex.org/W3007985585","https://openalex.org/W3011877239","https://openalex.org/W3013679533","https://openalex.org/W3031447301","https://openalex.org/W3035644784","https://openalex.org/W3037742481","https://openalex.org/W3037792667","https://openalex.org/W3038180127","https://openalex.org/W3046235508","https://openalex.org/W3093055384","https://openalex.org/W3101925693","https://openalex.org/W3102039646","https://openalex.org/W3103456419","https://openalex.org/W3112804989","https://openalex.org/W3129058148","https://openalex.org/W3138294267","https://openalex.org/W3150718622","https://openalex.org/W3195923278","https://openalex.org/W4210270608","https://openalex.org/W4211081235","https://openalex.org/W4211147054","https://openalex.org/W4214717370","https://openalex.org/W4224306019","https://openalex.org/W4241841688","https://openalex.org/W4287330329","https://openalex.org/W4287828546","https://openalex.org/W4294555834","https://openalex.org/W4294562617","https://openalex.org/W4295231058","https://openalex.org/W4297792208","https://openalex.org/W4312322550","https://openalex.org/W4384789633","https://openalex.org/W6601359773","https://openalex.org/W6607311216","https://openalex.org/W6675894441","https://openalex.org/W6679257226","https://openalex.org/W6683397050","https://openalex.org/W6684663846","https://openalex.org/W6738483526","https://openalex.org/W6751535212","https://openalex.org/W6754302822","https://openalex.org/W6755864697","https://openalex.org/W6767019922","https://openalex.org/W6771217966","https://openalex.org/W6771448118","https://openalex.org/W6771598146","https://openalex.org/W6772082531","https://openalex.org/W6773400333","https://openalex.org/W6775261052","https://openalex.org/W6777834836","https://openalex.org/W6778083458","https://openalex.org/W6793242357","https://openalex.org/W6922309221"],"related_works":["https://openalex.org/W4244478748","https://openalex.org/W4223488648","https://openalex.org/W2134969820","https://openalex.org/W2251605416","https://openalex.org/W4389340727","https://openalex.org/W2210722882","https://openalex.org/W2534107666","https://openalex.org/W2119378540","https://openalex.org/W2117933783","https://openalex.org/W2560479139"],"abstract_inverted_index":{"Online":[0],"actor-critic":[1,124,197],"reinforcement":[2,69,125,198],"learning":[3,70,126,199],"is":[4,25,35,85,143,217],"concerned":[5],"with":[6,14,157],"training":[7,110],"an":[8,123],"agent":[9,81,127,164],"on-the-fly":[10],"via":[11],"dynamic":[12],"interaction":[13],"the":[15,19,22,77,80,83,96,117,131,137,140,162,169,175,190,193],"environment.":[16],"Due":[17],"to":[18,29],"specifics":[20],"of":[21,76,79,95,105,119,130,196],"application,":[23],"it":[24,34],"not":[26,91],"generally":[27],"possible":[28],"perform":[30],"long":[31],"pre-training,":[32],"as":[33,60],"commonly":[36],"done":[37],"in":[38,51,55,93,103,145,153,211],"off-line,":[39],"tabular":[40],"or":[41],"Monte-Carlo":[42],"mode.":[43],"Such":[44],"applications":[45,214],"may":[46,180,208],"be":[47,181,209],"found":[48],"more":[49],"frequently":[50],"industry,":[52],"rather":[53],"than":[54],"pure":[56],"digital":[57],"fields,":[58],"such":[59],"cloud":[61],"services,":[62],"video":[63],"games,":[64],"database":[65],"management,":[66],"etc.,":[67],"where":[68,215],"has":[71],"been":[72],"demonstrating":[73],"success.":[74],"Stability":[75],"closed-loop":[78,141],"plus":[82],"environment":[84,97,120],"a":[86,154,158],"major":[87],"challenge":[88],"here,":[89],"and":[90,99],"only":[92],"terms":[94,104],"safety":[98],"integrity,":[100],"but":[101],"also":[102],"sparing":[106],"resources":[107],"on":[108,202],"failed":[109],"episodes.":[111],"In":[112],"this":[113],"paper,":[114],"we":[115,187],"tackle":[116],"problem":[118],"stability":[121,133,142,216],"under":[122],"by":[128],"integration":[129],"Lyapunov":[132],"theory":[134],"tools.":[135],"Under":[136],"presented":[138,206],"approach,":[139],"secured":[144],"all":[146],"episodes":[147],"without":[148],"pre-training.":[149],"It":[150],"was":[151],"observed":[152],"case":[155],"study":[156],"mobile":[159,184],"robot":[160,185],"that":[161,189],"suggested":[163],"could":[165],"always":[166],"successfully":[167],"achieve":[168],"control":[170],"goal,":[171],"while":[172],"significantly":[173],"reducing":[174],"cost.":[176],"While":[177],"many":[178],"approaches":[179],"exploited":[182],"for":[183],"control,":[186],"suggest":[188],"experiments":[191],"showed":[192],"promising":[194],"potential":[195],"agents":[200],"based":[201],"Lyapunov-like":[203],"constraints.":[204],"The":[205],"methodology":[207],"utilized":[210],"safety-critical,":[212],"industrial":[213],"necessary.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}