{"id":"https://openalex.org/W4315471968","doi":"https://doi.org/10.1109/cdc51059.2022.9992369","title":"Linear Observer Learning by Temporal Difference","display_name":"Linear Observer Learning by Temporal Difference","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315471968","doi":"https://doi.org/10.1109/cdc51059.2022.9992369"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9992369","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9992369","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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":"2022 IEEE 61st 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/A5011757135","display_name":"Stefano Menchetti","orcid":null},"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":true,"raw_author_name":"Stefano Menchetti","raw_affiliation_strings":["IMT School for Advanced Studies Lucca,Lucca,Italy,55100"],"affiliations":[{"raw_affiliation_string":"IMT School for Advanced Studies Lucca,Lucca,Italy,55100","institution_ids":["https://openalex.org/I127077003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106707940","display_name":"Mario Zanon","orcid":"https://orcid.org/0000-0001-5925-0440"},"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":"Mario Zanon","raw_affiliation_strings":["IMT School for Advanced Studies Lucca,Lucca,Italy,55100"],"affiliations":[{"raw_affiliation_string":"IMT School for Advanced Studies Lucca,Lucca,Italy,55100","institution_ids":["https://openalex.org/I127077003"]}]},{"author_position":"last","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,Lucca,Italy,55100"],"affiliations":[{"raw_affiliation_string":"IMT School for Advanced Studies Lucca,Lucca,Italy,55100","institution_ids":["https://openalex.org/I127077003"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011757135"],"corresponding_institution_ids":["https://openalex.org/I127077003"],"apc_list":null,"apc_paid":null,"fwci":0.3539,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52305359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2777","last_page":"2782"},"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/T11236","display_name":"Control Systems and Identification","score":0.9955000281333923,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.750872015953064},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.7451463937759399},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6618005633354187},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.6579654216766357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6224474310874939},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.53943932056427},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4465039074420929},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4336877465248108},{"id":"https://openalex.org/keywords/state-observer","display_name":"State observer","score":0.43232831358909607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3439862132072449},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32290059328079224},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27701836824417114},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.1616734266281128},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.15409770607948303},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08260384202003479}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.750872015953064},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.7451463937759399},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6618005633354187},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6579654216766357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6224474310874939},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.53943932056427},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4465039074420929},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4336877465248108},{"id":"https://openalex.org/C3031470","wikidata":"https://www.wikidata.org/wiki/Q818544","display_name":"State observer","level":3,"score":0.43232831358909607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3439862132072449},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32290059328079224},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27701836824417114},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.1616734266281128},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.15409770607948303},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08260384202003479},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9992369","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9992369","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1981726496","https://openalex.org/W1995573301","https://openalex.org/W2020934227","https://openalex.org/W2037914955","https://openalex.org/W2064217415","https://openalex.org/W2072931156","https://openalex.org/W2105934661","https://openalex.org/W2122512809","https://openalex.org/W2128457724","https://openalex.org/W2143558629","https://openalex.org/W2160338492","https://openalex.org/W3041202696","https://openalex.org/W3094054501","https://openalex.org/W4214717370","https://openalex.org/W4232464081","https://openalex.org/W4252380473","https://openalex.org/W4388085068","https://openalex.org/W6784280521"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2394201814","https://openalex.org/W2154399718","https://openalex.org/W2544838361","https://openalex.org/W2315418312","https://openalex.org/W4321463377","https://openalex.org/W2113447317","https://openalex.org/W2501264310","https://openalex.org/W2768629321"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"method":[4,66],"for":[5,13,46,67],"learning":[6,29],"optimal":[7,73],"state":[8,48,68],"estimators":[9],"from":[10],"input/output":[11],"data":[12],"linear":[14],"discrete-time":[15],"stochastic":[16],"systems.":[17],"We":[18,58],"show":[19,59],"that":[20,62],"this":[21],"problem":[22,36,50],"can":[23],"be":[24],"expressed":[25],"in":[26,60],"the":[27,34,42,47,63,72],"reinforcement":[28],"framework,":[30],"suitably":[31],"adapted":[32],"to":[33,55,71],"peculiar":[35],"structure.":[37],"In":[38],"particular,":[39],"we":[40],"introduce":[41],"specific":[43],"Bellman":[44],"equation":[45],"estimation":[49,69],"and":[51],"use":[52],"temporal":[53],"differences":[54],"solve":[56],"it.":[57],"simulations":[61],"resulting":[64],"data-driven":[65],"converges":[70],"observer.":[74]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}