{"id":"https://openalex.org/W7117454635","doi":"https://doi.org/10.1109/summa68668.2025.11302275","title":"Reverse Engineering System Dynamics from Reinforcement Learning Q-Functions in LQR Settings","display_name":"Reverse Engineering System Dynamics from Reinforcement Learning Q-Functions in LQR Settings","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7117454635","doi":"https://doi.org/10.1109/summa68668.2025.11302275"},"language":"en","primary_location":{"id":"doi:10.1109/summa68668.2025.11302275","doi":"https://doi.org/10.1109/summa68668.2025.11302275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/summa68668.2025.11302275","pdf_url":null,"source":{"id":"https://openalex.org/S4363607907","display_name":"International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2025 7th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5031854085","display_name":"Joseph Julien Yame","orcid":"https://orcid.org/0000-0002-4349-6240","observed_orcids":["https://orcid.org/0000-0002-4349-6240"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210110792","display_name":"CRAN","ror":"https://ror.org/022r5hc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210099203","https://openalex.org/I4210100260","https://openalex.org/I4210110792","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Joseph-Julien Yam\u00e9","raw_affiliation_strings":["Université de Lorraine,CRAN, CNRS, UMR 7039,Vandoeuvre-lès-Nancy,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine,CRAN, CNRS, UMR 7039,Vandoeuvre-lès-Nancy,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210110792"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031854085"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210110792"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47733196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"518","last_page":"523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4099000096321106,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4099000096321106,"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/T11236","display_name":"Control Systems and Identification","score":0.3244999945163727,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.2483000010251999,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/system-identification","display_name":"system identification","score":0.6959999799728394},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"linear quadratic regulator","score":0.7829999923706055},{"id":"https://openalex.org/keywords/q-function","display_name":"Q-function","score":0.734000027179718},{"id":"https://openalex.org/keywords/coordinate-transformation","display_name":"coordinate transformation","score":0.6769999861717224},{"id":"https://openalex.org/keywords/identifiability","display_name":"identifiability","score":0.8320000171661377},{"id":"https://openalex.org/keywords/regularized-estimation","display_name":"regularized estimation","score":0.6179999709129333},{"id":"https://openalex.org/keywords/noisy-data","display_name":"noisy data","score":0.7459999918937683},{"id":"https://openalex.org/keywords/model-free-reinforcement-learning","display_name":"model-free reinforcement learning","score":0.8149999976158142}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7095999717712402},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.659600019454956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5938000082969666},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.4706999957561493},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.397599995136261},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.38760000467300415},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3822999894618988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3779999911785126},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3418000042438507},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C119247159","wikidata":"https://www.wikidata.org/wiki/Q1366192","display_name":"System identification","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C80551277","wikidata":"https://www.wikidata.org/wiki/Q11210","display_name":"Coordinate system","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/summa68668.2025.11302275","doi":"https://doi.org/10.1109/summa68668.2025.11302275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/summa68668.2025.11302275","pdf_url":null,"source":{"id":"https://openalex.org/S4363607907","display_name":"International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2025 7th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05424218v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.science/hal-05424218","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"7th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency, SUMMA 2025, Nov 2025, Lipetsk, Russia. pp.518-523, ⟨10.1109/SUMMA68668.2025.11302275⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2484646121","https://openalex.org/W2548411414","https://openalex.org/W3037667042","https://openalex.org/W4200561738","https://openalex.org/W4229706427","https://openalex.org/W4241492945","https://openalex.org/W4405846208","https://openalex.org/W4414715101"],"related_works":[],"abstract_inverted_index":{"This":[0,140],"paper":[1],"addresses":[2],"the":[3,8,21,26,38,48,58,92,100,127,132,137,154],"novel":[4],"problem":[5,93],"of":[6,10,64,69,82,156],"recovering":[7],"dynamics":[9,71,135],"a":[11,53,74,83,116],"linear":[12],"system":[13,39,49,134,151],"using":[14],"data":[15,103],"from":[16,20,160],"reinforcement":[17,106,148],"learning,":[18],"particularly":[19],"quality":[22,32,76],"function":[23,33,77],"associated":[24],"with":[25,73],"Linear":[27],"Quadratic":[28],"Regulator":[29],"(LQR).":[30],"The":[31,80],"implicitly":[34],"contains":[35],"information":[36],"about":[37],"dynamics,":[40],"but":[41],"it":[42,46],"is":[43,78,88],"shown":[44],"that":[45,56,126],"defines":[47],"only":[50],"up":[51],"to":[52],"coordinate":[54],"transformation":[55],"preserves":[57],"optimal":[59],"value":[60],"function.":[61],"A":[62,122],"characterization":[63],"this":[65],"entire":[66],"equivalence":[67],"class":[68],"underlying":[70],"consistent":[72],"given":[75],"given.":[79],"recovery":[81],"unique":[84],"physically":[85],"meaningful":[86],"model":[87],"resolved":[89],"by":[90],"framing":[91],"as":[94],"an":[95,143],"orthogonal":[96],"Procrustes":[97],"alignment,":[98],"leveraging":[99],"same":[101],"trajectory":[102],"used":[104],"for":[105,119],"learning.":[107],"Identifiability":[108],"conditions":[109],"and":[110,150],"practical":[111],"algorithms":[112],"are":[113],"provided,":[114],"including":[115],"regularized":[117],"variant":[118],"noisy":[120],"data.":[121],"numerical":[123],"example":[124],"demonstrates":[125],"method":[128],"can":[129],"exactly":[130],"recover":[131],"true":[133],"in":[136],"noiseless":[138],"case.":[139],"work":[141],"provides":[142],"innovative":[144],"link":[145],"between":[146],"model-free":[147],"learning":[149],"identification,":[152],"enabling":[153],"extraction":[155],"interpretable":[157],"physical":[158],"models":[159],"data-driven":[161],"controllers.":[162]},"counts_by_year":[],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2025-12-29T00:00:00"}