{"id":"https://openalex.org/W3010834964","doi":"https://doi.org/10.1109/cdc40024.2019.9029904","title":"Using Reinforcement Learning for Model-free Linear Quadratic Control with Process and Measurement Noises","display_name":"Using Reinforcement Learning for Model-free Linear Quadratic Control with Process and Measurement Noises","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3010834964","doi":"https://doi.org/10.1109/cdc40024.2019.9029904","mag":"3010834964"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9029904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029904","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036304677","display_name":"Farnaz Adib Yaghmaie","orcid":"https://orcid.org/0000-0002-6665-5881"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Farnaz Adib Yaghmaie","raw_affiliation_strings":["Department of Electrical Engineering, Linkping University, Linkping, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Linkping University, Linkping, Sweden","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058002446","display_name":"Fredrik Gustafsson","orcid":"https://orcid.org/0000-0003-3270-171X"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Fredrik Gustafsson","raw_affiliation_strings":["Faculty of Department of Electrical Engineering, Linkping University, Linkping, Sweden"],"affiliations":[{"raw_affiliation_string":"Faculty of Department of Electrical Engineering, Linkping University, Linkping, Sweden","institution_ids":["https://openalex.org/I102134673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036304677"],"corresponding_institution_ids":["https://openalex.org/I102134673"],"apc_list":null,"apc_paid":null,"fwci":0.582,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.72115755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6510","last_page":"6517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9995999932289124,"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":0.9955000281333923,"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8821667432785034},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6919994354248047},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5680943131446838},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5463954210281372},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5308961272239685},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5301899313926697},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5231905579566956},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.5139917731285095},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49492043256759644},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.4697081446647644},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44866734743118286},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4042384624481201},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3299725651741028},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29967230558395386},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.200152188539505}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8821667432785034},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6919994354248047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5680943131446838},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5463954210281372},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5308961272239685},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5301899313926697},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5231905579566956},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.5139917731285095},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49492043256759644},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.4697081446647644},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44866734743118286},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4042384624481201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3299725651741028},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29967230558395386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.200152188539505},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":1,"locations":[{"id":"doi:10.1109/cdc40024.2019.9029904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029904","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1876438114","https://openalex.org/W1972243698","https://openalex.org/W2008229822","https://openalex.org/W2011866373","https://openalex.org/W2015881065","https://openalex.org/W2090167557","https://openalex.org/W2098432798","https://openalex.org/W2107726111","https://openalex.org/W2145339207","https://openalex.org/W2152161277","https://openalex.org/W2165418472","https://openalex.org/W2165726932","https://openalex.org/W2331243380","https://openalex.org/W2580629550","https://openalex.org/W2761923184","https://openalex.org/W2822752092","https://openalex.org/W2850875954","https://openalex.org/W2886474253","https://openalex.org/W2900809720","https://openalex.org/W2926824550","https://openalex.org/W2964084913","https://openalex.org/W2974120149","https://openalex.org/W4214717370","https://openalex.org/W4295092823","https://openalex.org/W6745072325","https://openalex.org/W6746722099","https://openalex.org/W6752646424","https://openalex.org/W6752937632","https://openalex.org/W6754297394"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3099153698","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2025663273"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"analyze":[4],"a":[5,26],"Linear":[6],"Quadratic":[7],"(LQ)":[8],"control":[9],"problem":[10],"in":[11],"terms":[12],"of":[13,20],"the":[14,18,21,34,58,65,74],"average":[15],"cost":[16],"and":[17,77],"structure":[19],"value":[22,53],"function.":[23],"We":[24,55],"develop":[25],"completely":[27],"model-free":[28],"reinforcement":[29],"learning":[30,79],"algorithm":[31,38,59,72],"to":[32,50],"solve":[33],"LQ":[35],"problem.":[36],"Our":[37],"is":[39,46],"an":[40],"off-policy":[41,78],"routine":[42],"where":[43],"each":[44],"policy":[45],"greedy":[47],"with":[48],"respect":[49],"all":[51],"previous":[52],"functions.":[54],"prove":[56],"that":[57,64],"produces":[60],"stable":[61],"policies":[62],"given":[63],"estimation":[66],"errors":[67],"remain":[68],"small.":[69],"Empirically,":[70],"our":[71],"outperforms":[73],"classical":[75],"Q":[76],"routines.":[80]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}