{"id":"https://openalex.org/W3195923278","doi":"https://doi.org/10.1109/tac.2023.3250032","title":"A Generalized Stacked Reinforcement Learning Method for Sampled Systems","display_name":"A Generalized Stacked Reinforcement Learning Method for Sampled Systems","publication_year":2023,"publication_date":"2023-02-27","ids":{"openalex":"https://openalex.org/W3195923278","doi":"https://doi.org/10.1109/tac.2023.3250032","mag":"3195923278"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2023.3250032","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tac.2023.3250032","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-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/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/A5051035411","display_name":"Dmitrii Dobriborsci","orcid":"https://orcid.org/0000-0002-1091-7459"},"institutions":[{"id":"https://openalex.org/I83041830","display_name":"Deggendorf Institute of Technology","ror":"https://ror.org/02kw5st29","country_code":"DE","type":"education","lineage":["https://openalex.org/I83041830"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dmitrii Dobriborsci","raw_affiliation_strings":["Deggendorf Institute of Technology, Cham, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1091-7459","affiliations":[{"raw_affiliation_string":"Deggendorf Institute of Technology, Cham, Germany","institution_ids":["https://openalex.org/I83041830"]}]},{"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":"last","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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.269,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82138181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"68","issue":"11","first_page":"7006","last_page":"7013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9945999979972839,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9850000143051147,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8770312070846558},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8163403272628784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6810120344161987},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6644414663314819},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6573517918586731},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5032956004142761},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.49953150749206543},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.4876664876937866},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.45653754472732544},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4395272135734558},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4170064628124237},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4163307845592499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.368497371673584},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19854798913002014}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8770312070846558},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8163403272628784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6810120344161987},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6644414663314819},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6573517918586731},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5032956004142761},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49953150749206543},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.4876664876937866},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.45653754472732544},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4395272135734558},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4170064628124237},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4163307845592499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.368497371673584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19854798913002014},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2023.3250032","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tac.2023.3250032","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W1988505764","https://openalex.org/W2040161377","https://openalex.org/W2113501460","https://openalex.org/W2196218134","https://openalex.org/W2220314357","https://openalex.org/W2281096776","https://openalex.org/W2548618581","https://openalex.org/W2618318883","https://openalex.org/W2767143830","https://openalex.org/W2772982620","https://openalex.org/W2890141553","https://openalex.org/W2898035736","https://openalex.org/W2902624920","https://openalex.org/W2902907165","https://openalex.org/W2948652605","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3030804074","https://openalex.org/W3037827181","https://openalex.org/W3046235508","https://openalex.org/W3046709980","https://openalex.org/W3092793148","https://openalex.org/W3100539220","https://openalex.org/W3122336430","https://openalex.org/W3131040061","https://openalex.org/W3138294267","https://openalex.org/W3155511388","https://openalex.org/W3189722490","https://openalex.org/W3199004685","https://openalex.org/W4294555834","https://openalex.org/W4297792208","https://openalex.org/W6738483526","https://openalex.org/W6746717651","https://openalex.org/W6758907457","https://openalex.org/W6772005887","https://openalex.org/W6778083458","https://openalex.org/W6786261308"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W4308702637","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W1859185863","https://openalex.org/W2016648086","https://openalex.org/W2156021013","https://openalex.org/W1574958246"],"abstract_inverted_index":{"A":[0,40],"common":[1],"setting":[2],"of":[3,43,46,51],"reinforcement":[4],"learning":[5,102],"(RL)":[6],"is":[7,17,45,76,112,117],"a":[8,18,71,77,125],"Markov":[9],"decision":[10],"process":[11],"(MDP)":[12],"in":[13,27,63,119],"which":[14],"the":[15,52,103],"environment":[16],"stochastic":[19],"discrete-time":[20],"dynamical":[21],"system.":[22],"Whereas":[23],"MDPs":[24],"are":[25,37,58],"suitable":[26,90],"such":[28],"applications":[29],"as":[30],"video":[31],"games":[32],"or":[33],"puzzles,":[34],"physical":[35],"systems":[36],"time":[38],"continuous.":[39],"general":[41],"variant":[42],"RL":[44,88],"digital":[47],"format,":[48],"where":[49],"updates":[50],"value":[53,107],"(or":[54,108],"cost)":[55],"and":[56,85,106,114],"policy":[57],"performed":[59],"at":[60],"discrete":[61],"moments":[62],"time.":[64],"The":[65],"agent\u2013environment":[66],"loop":[67],"then":[68],"amounts":[69],"to":[70],"sampled":[72,92],"system,":[73],"whereby":[74],"sample-and-hold":[75],"specific":[78],"case.":[79],"In":[80],"this":[81],"article,":[82],"we":[83,95],"propose":[84],"benchmark":[86],"two":[87],"methods":[89],"for":[91],"systems.":[93],"Specifically,":[94],"hybridize":[96],"model":[97],"predictive":[98],"control":[99],"with":[100,124],"critics":[101],"optimal":[104],"Q-":[105],"cost-to-go)":[109],"function.":[110],"Optimality":[111],"analyzed":[113],"performance":[115],"comparison":[116],"done":[118],"an":[120],"experimental":[121],"case":[122],"study":[123],"mobile":[126],"robot.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}