{"id":"https://openalex.org/W3139302403","doi":"https://doi.org/10.23919/acc50511.2021.9483399","title":"Reinforcement Learning based on MPC/MHE for Unmodeled and Partially Observable Dynamics","display_name":"Reinforcement Learning based on MPC/MHE for Unmodeled and Partially Observable Dynamics","publication_year":2021,"publication_date":"2021-05-25","ids":{"openalex":"https://openalex.org/W3139302403","doi":"https://doi.org/10.23919/acc50511.2021.9483399","mag":"3139302403"},"language":"en","primary_location":{"id":"doi:10.23919/acc50511.2021.9483399","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc50511.2021.9483399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 American Control Conference (ACC)","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/2103.11871","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011634446","display_name":"Hossein Nejatbakhsh Esfahani","orcid":"https://orcid.org/0000-0003-3515-1645"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Hossein Nejatbakhsh Esfahani","raw_affiliation_strings":["Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","Norwegian University of Science and Technology (NTNU) - Department of Engineering Cybernetics, Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU) - Department of Engineering Cybernetics, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033874726","display_name":"Arash Bahari Kordabad","orcid":"https://orcid.org/0000-0001-8931-5372"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Arash Bahari Kordabad","raw_affiliation_strings":["Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","Norwegian University of Science and Technology (NTNU) - Department of Engineering Cybernetics, Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU) - Department of Engineering Cybernetics, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049645185","display_name":"S\u00e9bastien Gros","orcid":"https://orcid.org/0000-0001-6054-2133"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Sebastien Gros","raw_affiliation_strings":["Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","Norwegian University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Norwegian University of Science and Technology","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204778367"],"apc_list":null,"apc_paid":null,"fwci":3.15,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92548442,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2121","last_page":"2126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9994999766349792,"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":0.9994999766349792,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9878000020980835,"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/observable","display_name":"Observable","score":0.8113599419593811},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.7928550243377686},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7726003527641296},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7521407604217529},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6775719523429871},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.6766326427459717},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.636357307434082},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6261870861053467},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.5375077724456787},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47047120332717896},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.41086363792419434},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4101862907409668},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4017221927642822},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.36529529094696045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23988714814186096},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21220985054969788}],"concepts":[{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.8113599419593811},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7928550243377686},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7726003527641296},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7521407604217529},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6775719523429871},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6766326427459717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.636357307434082},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6261870861053467},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.5375077724456787},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47047120332717896},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.41086363792419434},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4101862907409668},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4017221927642822},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.36529529094696045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23988714814186096},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21220985054969788},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.23919/acc50511.2021.9483399","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc50511.2021.9483399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.11871","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.11871","pdf_url":"https://arxiv.org/pdf/2103.11871","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3139302403","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.11871.pdf","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.2103.11871","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.11871","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.11871","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.11871","pdf_url":"https://arxiv.org/pdf/2103.11871","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3139302403.pdf","grobid_xml":"https://content.openalex.org/works/W3139302403.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2073787051","https://openalex.org/W2088871537","https://openalex.org/W2091638547","https://openalex.org/W2098432798","https://openalex.org/W2121863487","https://openalex.org/W2151966330","https://openalex.org/W2786312736","https://openalex.org/W2810195925","https://openalex.org/W2897090992","https://openalex.org/W2900559324","https://openalex.org/W2930426397","https://openalex.org/W2939873520","https://openalex.org/W2952032963","https://openalex.org/W2967513726","https://openalex.org/W2968286045","https://openalex.org/W2968296759","https://openalex.org/W2968788589","https://openalex.org/W3014923917","https://openalex.org/W3029645440","https://openalex.org/W3147547649","https://openalex.org/W6674995601","https://openalex.org/W6752833377","https://openalex.org/W6755999739","https://openalex.org/W6764926043","https://openalex.org/W6775739304"],"related_works":["https://openalex.org/W3185747626","https://openalex.org/W3098187358","https://openalex.org/W3204685159","https://openalex.org/W2083522486","https://openalex.org/W3012765523","https://openalex.org/W2380503381","https://openalex.org/W2503017641","https://openalex.org/W2058445812","https://openalex.org/W2986310176","https://openalex.org/W2885491722","https://openalex.org/W2333199498","https://openalex.org/W3115173719","https://openalex.org/W2911766239","https://openalex.org/W2557055507","https://openalex.org/W3163723204","https://openalex.org/W2926270496","https://openalex.org/W2919774326","https://openalex.org/W2114839191","https://openalex.org/W2443039537","https://openalex.org/W1993171261"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,15],"observer-based":[4],"framework":[5],"for":[6,40,73,80],"solving":[7],"Partially":[8],"Observable":[9],"Markov":[10],"Decision":[11],"Processes":[12],"(POMDPs)":[13],"when":[14],"accurate":[16],"model":[17,119],"is":[18,52],"not":[19,53],"available.":[20],"We":[21,58],"first":[22],"propose":[23,59],"to":[24,36,60,97],"use":[25],"a":[26,38,115],"Moving":[27],"Horizon":[28],"Estimation-Model":[29],"Predictive":[30],"Control":[31],"(MHE-MPC)":[32],"scheme":[33],"in":[34],"order":[35],"provide":[37],"policy":[39,113],"the":[41,45,49,75,81,85,93,99,108,112,122,128,134],"POMDP":[42],"problem,":[43],"where":[44,67],"full":[46],"state":[47],"of":[48,83,101,111,136,139],"real":[50],"process":[51],"measured":[54],"and":[55,64,87,103],"necessarily":[56],"known.":[57],"parameterize":[61],"both":[62],"MPC":[63,102],"MHE":[65,104,123],"formulations,":[66],"certain":[68],"adjustable":[69],"parameters":[70,100],"are":[71],"regarded":[72],"tuning":[74],"policy.":[76],"In":[77],"this":[78],"paper,":[79],"sake":[82],"tackling":[84],"unmodeled":[86],"partially":[88],"observable":[89],"dynamics,":[90],"we":[91],"leverage":[92],"Reinforcement":[94],"Learning":[95],"(RL)":[96],"tune":[98],"schemes":[105],"jointly,":[106],"with":[107],"closed-loop":[109],"performance":[110,135],"as":[114,142],"goal":[116],"rather":[117],"than":[118],"fitting":[120],"or":[121],"performance.":[124],"Illustrations":[125],"show":[126],"that":[127],"proposed":[129],"approach":[130],"can":[131],"effectively":[132],"increase":[133],"close-loop":[137],"control":[138],"systems":[140],"formulated":[141],"POMDPs.":[143]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}