{"id":"https://openalex.org/W2948661064","doi":"https://doi.org/10.1109/cdc40024.2019.9030185","title":"Model predictive control with stage cost shaping inspired by reinforcement learning","display_name":"Model predictive control with stage cost shaping inspired by reinforcement learning","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2948661064","doi":"https://doi.org/10.1109/cdc40024.2019.9030185","mag":"2948661064"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9030185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9030185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.02580","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067098516","display_name":"Lukas Beckenbach","orcid":"https://orcid.org/0000-0001-8680-3311"},"institutions":[{"id":"https://openalex.org/I2610724","display_name":"Chemnitz University of Technology","ror":"https://ror.org/00a208s56","country_code":"DE","type":"education","lineage":["https://openalex.org/I2610724"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lukas Beckenbach","raw_affiliation_strings":["Automatic Control and System Dynamics Laboratory, Technische Universit\u00e4t Chemnitz, Chemnitz, Germany","Technische Universit\u00e4t Chemnitz,Automatic Control and System Dynamics Laboratory,Chemnitz,Germany,09107"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Automatic Control and System Dynamics Laboratory, Technische Universit\u00e4t Chemnitz, Chemnitz, Germany","institution_ids":["https://openalex.org/I2610724"]},{"raw_affiliation_string":"Technische Universit\u00e4t Chemnitz,Automatic Control and System Dynamics Laboratory,Chemnitz,Germany,09107","institution_ids":["https://openalex.org/I2610724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065280230","display_name":"Pavel Osinenko","orcid":"https://orcid.org/0000-0002-6184-3293"},"institutions":[{"id":"https://openalex.org/I2610724","display_name":"Chemnitz University of Technology","ror":"https://ror.org/00a208s56","country_code":"DE","type":"education","lineage":["https://openalex.org/I2610724"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pavel Osinenko","raw_affiliation_strings":["Automatic Control and System Dynamics Laboratory, Technische Universit\u00e4t Chemnitz, Chemnitz, Germany","Technische Universit\u00e4t Chemnitz,Automatic Control and System Dynamics Laboratory,Chemnitz,Germany,09107"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Automatic Control and System Dynamics Laboratory, Technische Universit\u00e4t Chemnitz, Chemnitz, Germany","institution_ids":["https://openalex.org/I2610724"]},{"raw_affiliation_string":"Technische Universit\u00e4t Chemnitz,Automatic Control and System Dynamics Laboratory,Chemnitz,Germany,09107","institution_ids":["https://openalex.org/I2610724"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050202669","display_name":"Stefan Streif","orcid":"https://orcid.org/0000-0002-3398-1226"},"institutions":[{"id":"https://openalex.org/I2610724","display_name":"Chemnitz University of Technology","ror":"https://ror.org/00a208s56","country_code":"DE","type":"education","lineage":["https://openalex.org/I2610724"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Streif","raw_affiliation_strings":["Automatic Control and System Dynamics Laboratory, Technische Universit\u00e4t Chemnitz, Chemnitz, Germany","[Chemnitz University of Technology]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Automatic Control and System Dynamics Laboratory, Technische Universit\u00e4t Chemnitz, Chemnitz, Germany","institution_ids":["https://openalex.org/I2610724"]},{"raw_affiliation_string":"[Chemnitz University of Technology]","institution_ids":["https://openalex.org/I2610724"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2610724"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04166846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7110","last_page":"7115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9998999834060669,"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":0.9983000159263611,"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":0.996399998664856,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8210266828536987},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.7569856643676758},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6355308890342712},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.6205897331237793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.555083155632019},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5503973364830017},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.48660075664520264},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44780057668685913},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4466250538825989},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44370776414871216},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.43876194953918457},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.40508052706718445},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3187106251716614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3179236352443695}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8210266828536987},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.7569856643676758},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6355308890342712},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.6205897331237793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.555083155632019},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5503973364830017},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.48660075664520264},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44780057668685913},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4466250538825989},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44370776414871216},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.43876194953918457},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.40508052706718445},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3187106251716614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3179236352443695},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cdc40024.2019.9030185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9030185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.02580","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.02580","pdf_url":"https://arxiv.org/pdf/1906.02580","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2948661064","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1906.02580","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1906.02580","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.02580","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.02580","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.02580","pdf_url":"https://arxiv.org/pdf/1906.02580","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2948661064.pdf","grobid_xml":"https://content.openalex.org/works/W2948661064.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1978956894","https://openalex.org/W1988505764","https://openalex.org/W1993171261","https://openalex.org/W2003502661","https://openalex.org/W2024122443","https://openalex.org/W2041109651","https://openalex.org/W2062915697","https://openalex.org/W2096164155","https://openalex.org/W2100677568","https://openalex.org/W2111980775","https://openalex.org/W2116488102","https://openalex.org/W2150339816","https://openalex.org/W2158091072","https://openalex.org/W2161040592","https://openalex.org/W2163148228","https://openalex.org/W2165545652","https://openalex.org/W2165726932","https://openalex.org/W2173248099","https://openalex.org/W2516720609","https://openalex.org/W2948652605","https://openalex.org/W2963683522","https://openalex.org/W3041202696","https://openalex.org/W3139377883","https://openalex.org/W6684921986","https://openalex.org/W6763565325"],"related_works":["https://openalex.org/W1978956894","https://openalex.org/W2140586826","https://openalex.org/W2014022121","https://openalex.org/W2963543350","https://openalex.org/W2059061259","https://openalex.org/W2621300244","https://openalex.org/W2328684404","https://openalex.org/W3032383245","https://openalex.org/W2288359064","https://openalex.org/W2262593276","https://openalex.org/W2286696732","https://openalex.org/W3153256836","https://openalex.org/W2296360731","https://openalex.org/W2995333107","https://openalex.org/W1878168572","https://openalex.org/W1999536259","https://openalex.org/W2964004191","https://openalex.org/W2151896566","https://openalex.org/W1983859989","https://openalex.org/W2952088374"],"abstract_inverted_index":{"This":[0],"work":[1,92],"presents":[2],"a":[3,7,60,64,71,85],"suboptimality":[4],"study":[5,27],"of":[6,20,25,40,59,70,83,104],"particular":[8,86],"model":[9,41],"predictive":[10,42],"control":[11,43,52],"with":[12,98],"stage":[13,76],"cost":[14,35,66,77],"shaping":[15],"based":[16],"on":[17],"the":[18,26,33,37,45,68,81],"ideas":[19],"reinforcement":[21,89],"learning.":[22,90],"The":[23,50,75,91],"focus":[24],"is":[28,78,93],"to":[29,44,88],"derive":[30],"quantities":[31],"relating":[32],"infinite-horizon":[34,47],"under":[36],"said":[38],"variant":[39],"respective":[46],"value":[48],"function.":[49,74],"basis":[51],"scheme":[53],"involves":[54],"usual":[55],"stabilizing":[56],"constraints":[57],"comprising":[58],"terminal":[61,65],"set":[62],"and":[63],"in":[67],"form":[69],"local":[72],"Lyapunov":[73],"adapted":[79],"using":[80],"principles":[82],"Q-learning,":[84],"approach":[87],"concluded":[94],"by":[95],"case":[96],"studies":[97],"two":[99],"systems":[100],"for":[101],"wide":[102],"ranges":[103],"initial":[105],"conditions.":[106]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2022-07-29T00:00:00"}