{"id":"https://openalex.org/W3146968663","doi":"https://doi.org/10.23919/ecc54610.2021.9654962","title":"Bias Correction in Deterministic Policy Gradient Using Robust MPC","display_name":"Bias Correction in Deterministic Policy Gradient Using Robust MPC","publication_year":2021,"publication_date":"2021-06-29","ids":{"openalex":"https://openalex.org/W3146968663","doi":"https://doi.org/10.23919/ecc54610.2021.9654962","mag":"3146968663"},"language":"en","primary_location":{"id":"doi:10.23919/ecc54610.2021.9654962","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc54610.2021.9654962","pdf_url":null,"source":{"id":"https://openalex.org/S4363608272","display_name":"2021 European Control Conference (ECC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 European Control Conference (ECC)","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/2104.02413","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","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":["Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU), 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":["Norwegian University of Science and Technology (NTNU), Trondheim, Norway","Norwegian University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03205737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1086","last_page":"1091"},"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9796000123023987,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.9753000140190125,"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/isotropy","display_name":"Isotropy","score":0.6105219125747681},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5409094095230103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5184428691864014},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5076130628585815},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.48945772647857666},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45891910791397095},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45684799551963806},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3484576344490051},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3414424657821655},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2700275480747223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13178381323814392},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11224684119224548}],"concepts":[{"id":"https://openalex.org/C184050105","wikidata":"https://www.wikidata.org/wiki/Q273163","display_name":"Isotropy","level":2,"score":0.6105219125747681},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5409094095230103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5184428691864014},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5076130628585815},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.48945772647857666},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45891910791397095},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45684799551963806},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3484576344490051},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3414424657821655},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2700275480747223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13178381323814392},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11224684119224548},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/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/ecc54610.2021.9654962","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc54610.2021.9654962","pdf_url":null,"source":{"id":"https://openalex.org/S4363608272","display_name":"2021 European Control Conference (ECC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 European Control Conference (ECC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.02413","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02413","pdf_url":"https://arxiv.org/pdf/2104.02413","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":"","raw_type":"text"},{"id":"mag:3146968663","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2104.02413.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.2104.02413","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.02413","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:2104.02413","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02413","pdf_url":"https://arxiv.org/pdf/2104.02413","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3146968663.pdf","grobid_xml":"https://content.openalex.org/works/W3146968663.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2073787051","https://openalex.org/W2121863487","https://openalex.org/W2156737235","https://openalex.org/W2892521964","https://openalex.org/W2905111361","https://openalex.org/W2930426397","https://openalex.org/W2948652605","https://openalex.org/W3136876223","https://openalex.org/W3139302403","https://openalex.org/W3153654730","https://openalex.org/W3154863495","https://openalex.org/W3185528958","https://openalex.org/W6683195989","https://openalex.org/W6684205842","https://openalex.org/W6757787546","https://openalex.org/W6763565325"],"related_works":["https://openalex.org/W3185528958","https://openalex.org/W3110922453","https://openalex.org/W2314848498","https://openalex.org/W2902627156","https://openalex.org/W2901097874","https://openalex.org/W3108890229","https://openalex.org/W2333779298","https://openalex.org/W2278171066","https://openalex.org/W2898520854","https://openalex.org/W2473807142","https://openalex.org/W3034809398","https://openalex.org/W2278618761","https://openalex.org/W2889864909","https://openalex.org/W2975197937","https://openalex.org/W2946924892","https://openalex.org/W3035048301","https://openalex.org/W3201284918","https://openalex.org/W3160142734","https://openalex.org/W3174652807","https://openalex.org/W2292499642"],"abstract_inverted_index":{"In":[0],"this":[1,111],"paper,":[2],"we":[3,72,107],"discuss":[4],"the":[5,10,15,22,28,35,47,69,81,116],"deterministic":[6],"policy":[7,29,48,85],"gradient":[8,49,117],"using":[9],"Actor-Critic":[11],"methods":[12],"based":[13,59],"on":[14,56,60],"linear":[16],"compatible":[17],"advantage":[18],"function":[19],"approximator,":[20],"where":[21],"input":[23],"spaces":[24],"are":[25],"continuous.":[26],"When":[27],"is":[30,94,100],"restricted":[31],"by":[32],"hard":[33],"constraints,":[34],"exploration":[36,93],"may":[37],"not":[38,114],"be":[39,52],"Centred":[40],"or":[41],"Isotropic":[42,91],"(non-CI).":[43],"As":[44],"a":[45,88],"result,":[46],"estimation":[50],"can":[51],"biased.":[53],"We":[54],"focus":[55],"constrained":[57],"policies":[58],"Model":[61],"Predictive":[62],"Control":[63],"(MPC)":[64],"schemes":[65],"and":[66,90],"to":[67,102],"address":[68],"bias":[70,115],"issue,":[71],"propose":[73],"an":[74],"approximate":[75],"Robust":[76],"MPC":[77],"approach":[78,112],"accounting":[79],"for":[80],"exploration.":[82],"The":[83],"RMPC-based":[84],"ensures":[86],"that":[87,110],"Centered":[89],"(CI)":[92],"approximately":[95],"feasible.":[96],"A":[97],"posterior":[98],"projection":[99],"used":[101],"ensure":[103],"its":[104],"exact":[105],"feasibility,":[106],"formally":[108],"prove":[109],"does":[113],"estimation.":[118]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
