{"id":"https://openalex.org/W4379472268","doi":"https://doi.org/10.1109/access.2023.3282842","title":"Variance-Based Exploration for Learning Model Predictive Control","display_name":"Variance-Based Exploration for Learning Model Predictive Control","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4379472268","doi":"https://doi.org/10.1109/access.2023.3282842"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3282842","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3282842","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10143647.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/ielx7/6287639/10005208/10143647.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078486239","display_name":"Katrine Seel","orcid":"https://orcid.org/0000-0003-2488-2784"},"institutions":[{"id":"https://openalex.org/I173888879","display_name":"SINTEF","ror":"https://ror.org/01f677e56","country_code":"NO","type":"facility","lineage":["https://openalex.org/I173888879"]},{"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"]},{"id":"https://openalex.org/I4387930215","display_name":"SINTEF Digital","ror":"https://ror.org/028m52w57","country_code":null,"type":"facility","lineage":["https://openalex.org/I173888879","https://openalex.org/I4387930215"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Katrine Seel","raw_affiliation_strings":["Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","Department of Mathematics and Cybernetics, SINTEF Digital, Oslo, Norway"],"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":"Department of Mathematics and Cybernetics, SINTEF Digital, Oslo, Norway","institution_ids":["https://openalex.org/I173888879","https://openalex.org/I4387930215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053340099","display_name":"Alberto Bemporad","orcid":"https://orcid.org/0000-0001-6761-0856"},"institutions":[{"id":"https://openalex.org/I127077003","display_name":"IMT School for Advanced Studies Lucca","ror":"https://ror.org/035gh3a49","country_code":"IT","type":"education","lineage":["https://openalex.org/I127077003"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Bemporad","raw_affiliation_strings":["IMT School for Advanced Studies, Lucca, Italy"],"affiliations":[{"raw_affiliation_string":"IMT School for Advanced Studies, Lucca, Italy","institution_ids":["https://openalex.org/I127077003"]}]},{"author_position":"middle","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":"S\u00e9bastien Gros","raw_affiliation_strings":["Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034485872","display_name":"Jan Tommy Gravdahl","orcid":"https://orcid.org/0000-0002-5663-0795"},"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":"Jan Tommy Gravdahl","raw_affiliation_strings":["Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078486239"],"corresponding_institution_ids":["https://openalex.org/I173888879","https://openalex.org/I204778367","https://openalex.org/I4387930215"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.5464,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64584886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"11","issue":null,"first_page":"60724","last_page":"60736"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9976999759674072,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6649921536445618},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6633124947547913},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6494672298431396},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6185446381568909},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5742506980895996},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5394208431243896},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5163372755050659},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5124221444129944},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5021700859069824},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44093140959739685},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3355370759963989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3340768814086914},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2670783996582031},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.24139404296875}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6649921536445618},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6633124947547913},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6494672298431396},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6185446381568909},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5742506980895996},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5394208431243896},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5163372755050659},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5124221444129944},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5021700859069824},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44093140959739685},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3355370759963989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3340768814086914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2670783996582031},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.24139404296875},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2023.3282842","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3282842","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10143647.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7ce8fab61eb44948952602195d8a3fff","is_oa":true,"landing_page_url":"https://doaj.org/article/7ce8fab61eb44948952602195d8a3fff","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 60724-60736 (2023)","raw_type":"article"},{"id":"pmh:oai:ntnuopen.ntnu.no:11250/3105167","is_oa":true,"landing_page_url":"https://hdl.handle.net/11250/3105167","pdf_url":null,"source":{"id":"https://openalex.org/S4306401716","display_name":"Duo Research Archive (University of Oslo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184942183","host_organization_name":"University of Oslo","host_organization_lineage":["https://openalex.org/I184942183"],"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":"60724-60736","raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3282842","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3282842","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10143647.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2056439586","display_name":null,"funder_award_id":"294544","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"},{"id":"https://openalex.org/G2096367874","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"},{"id":"https://openalex.org/G3748656914","display_name":null,"funder_award_id":"Norway","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"},{"id":"https://openalex.org/G716115180","display_name":null,"funder_award_id":"300172","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"}],"funders":[{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379472268.pdf","grobid_xml":"https://content.openalex.org/works/W4379472268.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1573878755","https://openalex.org/W2006859604","https://openalex.org/W2049312801","https://openalex.org/W2147169375","https://openalex.org/W2168405694","https://openalex.org/W2169209873","https://openalex.org/W2489939061","https://openalex.org/W2619551236","https://openalex.org/W2767313115","https://openalex.org/W2930426397","https://openalex.org/W3045570412","https://openalex.org/W3105252106","https://openalex.org/W3119715644","https://openalex.org/W3216794596","https://openalex.org/W4214717370","https://openalex.org/W4233696721","https://openalex.org/W4234228486","https://openalex.org/W4286781802","https://openalex.org/W4313160026","https://openalex.org/W4313650483","https://openalex.org/W4394648282","https://openalex.org/W6627932998","https://openalex.org/W6632504492","https://openalex.org/W6634104297","https://openalex.org/W6638018090","https://openalex.org/W6695011786","https://openalex.org/W6738568706","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6745497480","https://openalex.org/W6755864697","https://openalex.org/W6864167167","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"The":[0,110,132,159],"combination":[1],"of":[2,86,88,134,152],"model":[3],"predictive":[4],"control":[5,19],"(MPC)":[6],"and":[7,54,118,130,171,175],"learning":[8,35],"methods":[9,180],"has":[10],"been":[11],"gaining":[12],"increasing":[13],"attention":[14],"as":[15,29,76],"a":[16,30,83,101,147],"tool":[17],"to":[18,25,40,52,81,116,141,177],"systems":[20],"that":[21],"may":[22],"be":[23],"difficult":[24],"model.":[26],"Using":[27],"MPC":[28,75],"function":[31,77,91,155],"approximator":[32,92],"in":[33,70,93,121,146],"reinforcement":[34],"(RL)":[36],"is":[37,48,98,113,138,157,162],"one":[38],"approach":[39],"reduce":[41],"the":[42,89,135,143,150,153],"reliance":[43],"on":[44,50,59,105,164],"accurate":[45],"models.":[46],"RL":[47,71,95],"dependent":[49],"exploration":[51,69,179],"learn,":[53],"currently,":[55],"simple":[56],"heuristics":[57],"based":[58,104],"random":[60,182],"perturbations":[61],"are":[62],"most":[63],"common.":[64],"This":[65],"paper":[66],"considers":[67],"variance-based":[68],"geared":[72],"towards":[73],"using":[74,125,181],"approximator.":[78],"We":[79],"propose":[80],"use":[82],"non-probabilistic":[84],"measure":[85],"uncertainty":[87],"value":[90,154],"value-based":[94],"methods.":[96],"Uncertainty":[97],"measured":[99],"by":[100],"variance":[102,136,151],"estimate":[103,137,156],"inverse":[106],"distance":[107],"weighting":[108],"(IDW).":[109],"IDW":[111],"framework":[112],"computationally":[114],"cheap":[115],"evaluate":[117],"therefore":[119],"well-suited":[120],"an":[122],"online":[123],"setting,":[124],"already":[126],"sampled":[127],"state":[128],"transitions":[129],"rewards.":[131],"gradient":[133],"then":[139],"used":[140],"perturb":[142],"policy":[144],"parameters":[145],"direction":[148],"where":[149],"increasing.":[158],"proposed":[160],"method":[161],"verified":[163],"two":[165],"simulation":[166],"examples,":[167],"considering":[168],"both":[169],"linear":[170],"nonlinear":[172],"system":[173],"dynamics,":[174],"compared":[176],"standard":[178],"perturbations.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
