{"id":"https://openalex.org/W4391021039","doi":"https://doi.org/10.1109/cdc49753.2023.10383846","title":"Safe Q-Learning for Continuous-Time Linear Systems","display_name":"Safe Q-Learning for Continuous-Time Linear Systems","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391021039","doi":"https://doi.org/10.1109/cdc49753.2023.10383846"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"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/A5065989635","display_name":"Soutrik Bandyopadhyay","orcid":"https://orcid.org/0000-0002-9303-2495"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soutrik Bandyopadhyay","raw_affiliation_strings":["Indian Institute of Technology Delhi,Department of Electrical Engineering,New Delhi,India","Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Delhi,Department of Electrical Engineering,New Delhi,India","institution_ids":["https://openalex.org/I68891433"]},{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034219830","display_name":"Shubhendu Bhasin","orcid":"https://orcid.org/0000-0002-8002-9684"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shubhendu Bhasin","raw_affiliation_strings":["Indian Institute of Technology Delhi,Department of Electrical Engineering,New Delhi,India","Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Delhi,Department of Electrical Engineering,New Delhi,India","institution_ids":["https://openalex.org/I68891433"]},{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I68891433"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"241","last_page":"246"},"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.983299970626831,"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"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9794999957084656,"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/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.6612802147865295},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5896950960159302},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5466786026954651},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.514779806137085},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48553821444511414},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.46427223086357117},{"id":"https://openalex.org/keywords/lti-system-theory","display_name":"LTI system theory","score":0.4581559896469116},{"id":"https://openalex.org/keywords/reciprocal","display_name":"Reciprocal","score":0.4581105411052704},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44856804609298706},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.440265029668808},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4365033507347107},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.41848060488700867},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3824349045753479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2613617181777954},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24576357007026672},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1874619424343109},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11513558030128479}],"concepts":[{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.6612802147865295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5896950960159302},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5466786026954651},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.514779806137085},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48553821444511414},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.46427223086357117},{"id":"https://openalex.org/C87698059","wikidata":"https://www.wikidata.org/wiki/Q1808960","display_name":"LTI system theory","level":3,"score":0.4581559896469116},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.4581105411052704},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44856804609298706},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.440265029668808},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4365033507347107},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.41848060488700867},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3824349045753479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2613617181777954},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24576357007026672},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1874619424343109},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11513558030128479},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W234738007","https://openalex.org/W1540245649","https://openalex.org/W1972243698","https://openalex.org/W1978316810","https://openalex.org/W1983523797","https://openalex.org/W1990005421","https://openalex.org/W1991927580","https://openalex.org/W1993170675","https://openalex.org/W2062373349","https://openalex.org/W2085194340","https://openalex.org/W2086975818","https://openalex.org/W2087063454","https://openalex.org/W2094387729","https://openalex.org/W2104843094","https://openalex.org/W2107478723","https://openalex.org/W2121832485","https://openalex.org/W2148439597","https://openalex.org/W2150123286","https://openalex.org/W2152161277","https://openalex.org/W2155527096","https://openalex.org/W2160698719","https://openalex.org/W2171505650","https://openalex.org/W2214884926","https://openalex.org/W2484646121","https://openalex.org/W2560504659","https://openalex.org/W2564717627","https://openalex.org/W2765311583","https://openalex.org/W2887709062","https://openalex.org/W2927564896","https://openalex.org/W2942027162","https://openalex.org/W2948652605","https://openalex.org/W2963525569","https://openalex.org/W2968547875","https://openalex.org/W2968945909","https://openalex.org/W2973076431","https://openalex.org/W2977676795","https://openalex.org/W3011120880","https://openalex.org/W3048735518","https://openalex.org/W3085930940","https://openalex.org/W3096740192","https://openalex.org/W3119933750","https://openalex.org/W3120459386","https://openalex.org/W3138294267","https://openalex.org/W3154507809","https://openalex.org/W3168522732","https://openalex.org/W3177241667","https://openalex.org/W3184253385","https://openalex.org/W4233696721","https://openalex.org/W4250589301","https://openalex.org/W6677067356","https://openalex.org/W6678518843","https://openalex.org/W6771707735","https://openalex.org/W6784829994"],"related_works":["https://openalex.org/W2203843426","https://openalex.org/W2053005959","https://openalex.org/W2049369111","https://openalex.org/W2096457574","https://openalex.org/W2144143333","https://openalex.org/W2299538996","https://openalex.org/W2027136373","https://openalex.org/W4386631510","https://openalex.org/W2276636510","https://openalex.org/W2105658174"],"abstract_inverted_index":{"Q-learning":[0,24,43,66,96],"is":[1],"a":[2,41,69,86],"promising":[3],"method":[4],"for":[5,10,17,22,45,97],"solving":[6],"optimal":[7,71],"control":[8,72,76,88],"problems":[9],"uncertain":[11],"systems":[12,50,99],"without":[13],"the":[14,53,64,91,109],"explicit":[15],"need":[16],"system":[18],"identification.":[19],"However,":[20],"approaches":[21],"continuous-time":[23,98],"have":[25],"limited":[26],"provable":[27],"safety":[28],"guarantees,":[29],"which":[30],"restrict":[31],"their":[32],"applicability":[33],"to":[34,51],"real-time":[35],"safety-critical":[36],"systems.":[37],"This":[38],"paper":[39],"proposes":[40],"safe":[42,65],"algorithm":[44],"partially":[46],"unknown":[47],"linear":[48,54],"time-invariant":[49],"solve":[52],"quadratic":[55],"regulator":[56],"problem":[57,67,73],"with":[58,100],"user-defined":[59],"state":[60,101],"constraints.":[61],"We":[62],"frame":[63],"as":[68],"constrained":[70],"using":[74],"reciprocal":[75],"barrier":[77],"functions":[78],"and":[79],"show":[80],"that":[81],"such":[82],"an":[83],"extension":[84],"provides":[85],"safety-assured":[87],"policy.":[89],"To":[90],"best":[92],"of":[93],"our":[94],"knowledge,":[95],"constraints":[102],"has":[103],"not":[104],"yet":[105],"been":[106],"reported":[107],"in":[108],"literature.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}