{"id":"https://openalex.org/W3147547649","doi":"https://doi.org/10.23919/ecc54610.2021.9654852","title":"MPC-based Reinforcement Learning for Economic Problems with Application to Battery Storage","display_name":"MPC-based Reinforcement Learning for Economic Problems with Application to Battery Storage","publication_year":2021,"publication_date":"2021-06-29","ids":{"openalex":"https://openalex.org/W3147547649","doi":"https://doi.org/10.23919/ecc54610.2021.9654852","mag":"3147547649"},"language":"en","primary_location":{"id":"doi:10.23919/ecc54610.2021.9654852","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc54610.2021.9654852","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/2104.02411","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/A5009821721","display_name":"Wenqi Cai","orcid":"https://orcid.org/0000-0002-2195-0203"},"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":"Wenqi Cai","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU), Trondheim, Norway","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":0.92591185,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2573","last_page":"2578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9861000180244446,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9817000031471252,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7951169013977051},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.6253346800804138},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5805178880691528},{"id":"https://openalex.org/keywords/homotopy","display_name":"Homotopy","score":0.5730198621749878},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5551368594169617},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5153664946556091},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5112226009368896},{"id":"https://openalex.org/keywords/battery","display_name":"Battery (electricity)","score":0.47003644704818726},{"id":"https://openalex.org/keywords/relaxation","display_name":"Relaxation (psychology)","score":0.4269855320453644},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4106791913509369},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28848081827163696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2735617160797119},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.11453598737716675}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7951169013977051},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6253346800804138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5805178880691528},{"id":"https://openalex.org/C5961521","wikidata":"https://www.wikidata.org/wiki/Q746083","display_name":"Homotopy","level":2,"score":0.5730198621749878},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5551368594169617},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5153664946556091},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5112226009368896},{"id":"https://openalex.org/C555008776","wikidata":"https://www.wikidata.org/wiki/Q267298","display_name":"Battery (electricity)","level":3,"score":0.47003644704818726},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.4269855320453644},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4106791913509369},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28848081827163696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2735617160797119},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.11453598737716675},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.23919/ecc54610.2021.9654852","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc54610.2021.9654852","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:2104.02411","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02411","pdf_url":"https://arxiv.org/pdf/2104.02411","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:3147547649","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.02411.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.2104.02411","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.02411","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:2104.02411","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02411","pdf_url":"https://arxiv.org/pdf/2104.02411","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3147547649.pdf","grobid_xml":"https://content.openalex.org/works/W3147547649.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1598019333","https://openalex.org/W2062778210","https://openalex.org/W2073787051","https://openalex.org/W2100254153","https://openalex.org/W2121863487","https://openalex.org/W2130005627","https://openalex.org/W2165150801","https://openalex.org/W2300303305","https://openalex.org/W2892521964","https://openalex.org/W2930426397","https://openalex.org/W3012518766","https://openalex.org/W3081549049","https://openalex.org/W3136876223","https://openalex.org/W3139302403","https://openalex.org/W3153654730","https://openalex.org/W4235623249","https://openalex.org/W6683204974","https://openalex.org/W6684205842"],"related_works":["https://openalex.org/W2930426397","https://openalex.org/W2121863487","https://openalex.org/W3127035336","https://openalex.org/W2990189926","https://openalex.org/W3100238596","https://openalex.org/W2015482176","https://openalex.org/W2611835223","https://openalex.org/W3177263063","https://openalex.org/W3004920191","https://openalex.org/W3192247041","https://openalex.org/W3129455439","https://openalex.org/W3023892840","https://openalex.org/W3149465558","https://openalex.org/W3036913794","https://openalex.org/W2811292668","https://openalex.org/W3177503484","https://openalex.org/W3200157983","https://openalex.org/W2523642882","https://openalex.org/W2972586385","https://openalex.org/W2103541323"],"abstract_inverted_index":{"In":[0],"this":[1,86],"paper,":[2],"we":[3,67,88],"are":[4],"interested":[5],"in":[6,50,80],"optimal":[7,17],"control":[8],"problems":[9],"with":[10],"purely":[11],"economic":[12],"costs,":[13],"which":[14],"often":[15],"yield":[16],"policies":[18],"having":[19],"a":[20,63,90,99,109,122,128],"(nearly)":[21,64],"bang-bang":[22,65],"structure.":[23],"We":[24,107],"focus":[25],"on":[26,30,94],"policy":[27,41,61,71,82,103,130],"approximations":[28],"based":[29,93],"Model":[31],"Predictive":[32],"Control":[33],"(MPC)":[34],"and":[35,115,124],"the":[36,39,46,51,60,70,81,95,102,105,118],"use":[37],"of":[38,53,101],"deterministic":[40],"gradient":[42,72,131],"method":[43,73,120],"to":[44,76],"optimize":[45],"MPC":[47],"closed-loop":[48],"performance":[49],"presence":[52],"unmodelled":[54],"stochasticity":[55],"or":[56],"model":[57],"error.":[58],"When":[59],"has":[62],"structure,":[66],"observe":[68],"that":[69,117],"can":[74],"struggle":[75],"produce":[77],"meaningful":[78],"steps":[79],"parameters.":[83],"To":[84],"tackle":[85],"issue,":[87],"propose":[89],"homotopy":[91],"strategy":[92],"interior-point":[96],"method,":[97],"providing":[98],"relaxation":[100],"during":[104],"learning.":[106],"investigate":[108],"specific":[110],"well-known":[111],"battery":[112],"storage":[113],"problem,":[114],"show":[116],"proposed":[119],"delivers":[121],"homogeneous":[123],"faster":[125],"learning":[126],"than":[127],"classical":[129],"approach.":[132]},"counts_by_year":[{"year":2021,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}