{"id":"https://openalex.org/W4391020205","doi":"https://doi.org/10.1109/cdc49753.2023.10383620","title":"Convex Q-Learning in Continuous Time with Application to Dispatch of Distributed Energy Resources","display_name":"Convex Q-Learning in Continuous Time with Application to Dispatch of Distributed Energy Resources","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391020205","doi":"https://doi.org/10.1109/cdc49753.2023.10383620"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383620","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":"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/A5100371042","display_name":"Fan L\u00fc","orcid":"https://orcid.org/0000-0002-8794-6944"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fan Lu","raw_affiliation_strings":["University of California,Department of Applied Mathmatics and Statistics,Santa Cruz,CA,USA,95064"],"affiliations":[{"raw_affiliation_string":"University of California,Department of Applied Mathmatics and Statistics,Santa Cruz,CA,USA,95064","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082058815","display_name":"Joel Mathias","orcid":"https://orcid.org/0000-0002-9711-4607"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joel Mathias","raw_affiliation_strings":["School of Electrical, Computer, and Energy Engineering, Arizona State University,Tempe,AZ,USA,85281"],"affiliations":[{"raw_affiliation_string":"School of Electrical, Computer, and Energy Engineering, Arizona State University,Tempe,AZ,USA,85281","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047988825","display_name":"Sean Meyn","orcid":"https://orcid.org/0000-0002-8558-365X"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Meyn","raw_affiliation_strings":["University of Florida,Department of Electrical and Computer Engineering,Gainesville,FL,USA,32611"],"affiliations":[{"raw_affiliation_string":"University of Florida,Department of Electrical and Computer Engineering,Gainesville,FL,USA,32611","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071892762","display_name":"Karanjit Kalsi","orcid":"https://orcid.org/0000-0003-1287-949X"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karanjit Kalsi","raw_affiliation_strings":["Pacific Northwest National Laboratory,Richland,WA,USA,99354"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory,Richland,WA,USA,99354","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100371042"],"corresponding_institution_ids":["https://openalex.org/I185103710"],"apc_list":null,"apc_paid":null,"fwci":0.2674,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56521614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1529","last_page":"1536"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9962000250816345,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9933000206947327,"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/bellman-equation","display_name":"Bellman equation","score":0.7146196365356445},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7065067291259766},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.65555739402771},{"id":"https://openalex.org/keywords/convex-function","display_name":"Convex function","score":0.5836555361747742},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.575791597366333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5636540651321411},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5474964380264282},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5195196270942688},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.4552156329154968},{"id":"https://openalex.org/keywords/convex-analysis","display_name":"Convex analysis","score":0.4474468529224396},{"id":"https://openalex.org/keywords/economic-dispatch","display_name":"Economic dispatch","score":0.42620405554771423},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4201878309249878},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34279581904411316},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.34086865186691284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18688172101974487},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.09167993068695068},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.0904705822467804}],"concepts":[{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7146196365356445},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7065067291259766},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.65555739402771},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.5836555361747742},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.575791597366333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5636540651321411},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5474964380264282},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5195196270942688},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.4552156329154968},{"id":"https://openalex.org/C12108790","wikidata":"https://www.wikidata.org/wiki/Q2234833","display_name":"Convex analysis","level":4,"score":0.4474468529224396},{"id":"https://openalex.org/C187633118","wikidata":"https://www.wikidata.org/wiki/Q1317949","display_name":"Economic dispatch","level":4,"score":0.42620405554771423},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4201878309249878},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34279581904411316},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.34086865186691284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18688172101974487},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.09167993068695068},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0904705822467804},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C89227174","wikidata":"https://www.wikidata.org/wiki/Q2388981","display_name":"Electric power system","level":3,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383620","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":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G7566079004","display_name":null,"funder_award_id":"W911NF2010055","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8205755443","display_name":null,"funder_award_id":"EPCN 1935389","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W120139811","https://openalex.org/W560518094","https://openalex.org/W615181874","https://openalex.org/W1967821692","https://openalex.org/W1991927580","https://openalex.org/W2015887728","https://openalex.org/W2027968610","https://openalex.org/W2102628180","https://openalex.org/W2121863487","https://openalex.org/W2139418546","https://openalex.org/W2160698719","https://openalex.org/W2327685928","https://openalex.org/W2591278223","https://openalex.org/W2912967921","https://openalex.org/W3012490472","https://openalex.org/W3155706437","https://openalex.org/W3183922633","https://openalex.org/W3210638057","https://openalex.org/W3216251000","https://openalex.org/W4211221179","https://openalex.org/W4225718698","https://openalex.org/W4315488689","https://openalex.org/W4383604498","https://openalex.org/W4391020572","https://openalex.org/W6733735857","https://openalex.org/W6845533454","https://openalex.org/W6854396549"],"related_works":["https://openalex.org/W2100100236","https://openalex.org/W2040676043","https://openalex.org/W1977643895","https://openalex.org/W3125145310","https://openalex.org/W2391091101","https://openalex.org/W2187449906","https://openalex.org/W2051968184","https://openalex.org/W2388570749","https://openalex.org/W2130502871","https://openalex.org/W2510140549"],"abstract_inverted_index":{"Convex":[0,71,102],"Q-learning":[1,72,103],"is":[2,87,93,108,113,119,133,148],"a":[3,14,27,47,60,109],"recent":[4],"approach":[5],"to":[6,122,137],"reinforcement":[7],"learning,":[8],"motivated":[9],"by":[10,89],"the":[11,20,42,64,85,96,116,127,146],"possibility":[12,21],"of":[13,22,25,63,70,98],"firmer":[15],"theory":[16,132,147],"for":[17,140,144],"convergence,":[18],"and":[19],"making":[23],"use":[24],"greater":[26],"priori":[28],"knowledge":[29],"regarding":[30],"policy":[31],"or":[32],"value":[33],"function":[34,106],"structure.":[35],"This":[36],"paper":[37],"explores":[38],"algorithm":[39,86],"design":[40],"in":[41,77,84,95,135],"continuous":[43],"time":[44],"domain,":[45],"with":[46,104],"finite-horizon":[48],"optimal":[49],"control":[50],"objective.":[51],"The":[52,57,80,131],"main":[53],"contributions":[54],"are":[55],"(i)":[56],"new":[58],"Q-ODE:":[59],"model-free":[61],"characterization":[62],"Hamilton-Jacobi-Bellman":[65],"equation.":[66],"(ii)":[67],"A":[68],"formulation":[69],"that":[73,115],"avoids":[74],"approximations":[75],"appearing":[76],"prior":[78],"work.":[79],"Bellman":[81],"error":[82],"used":[83],"defined":[88],"filtered":[90],"measurements,":[91],"which":[92,145],"necessary":[94],"presence":[97],"measurement":[99],"noise.":[100],"(iii)":[101],"linear":[105],"approximation":[107],"convex":[110],"program.":[111],"It":[112],"shown":[114],"constraint":[117],"region":[118],"bounded,":[120],"subject":[121],"an":[123],"exploration":[124],"condition":[125],"on":[126],"training":[128],"input.":[129],"(iv)":[130],"illustrated":[134],"application":[136],"resource":[138],"allocation":[139],"distributed":[141],"energy":[142],"resources,":[143],"ideally":[149],"suited.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}