{"id":"https://openalex.org/W4391020572","doi":"https://doi.org/10.1109/cdc49753.2023.10384289","title":"Convex Q Learning in a Stochastic Environment","display_name":"Convex Q Learning in a Stochastic Environment","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391020572","doi":"https://doi.org/10.1109/cdc49753.2023.10384289"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10384289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10384289","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/A5080310406","display_name":"Fan L\u00fc","orcid":"https://orcid.org/0000-0002-4932-3850"},"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":true,"raw_author_name":"Fan Lu","raw_affiliation_strings":["University of Florida,Department of Electrical and Computer Engineering,Gainesville,FL,32611"],"affiliations":[{"raw_affiliation_string":"University of Florida,Department of Electrical and Computer Engineering,Gainesville,FL,32611","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","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 P. Meyn","raw_affiliation_strings":["University of Florida,Department of Electrical and Computer Engineering,Gainesville,FL,32611"],"affiliations":[{"raw_affiliation_string":"University of Florida,Department of Electrical and Computer Engineering,Gainesville,FL,32611","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080310406"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":0.6993,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76959685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"776","last_page":"781"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9907000064849854,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9907000064849854,"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":0.983299970626831,"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/regular-polygon","display_name":"Regular polygon","score":0.493285596370697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4830092191696167},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21346956491470337},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.11753562092781067}],"concepts":[{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.493285596370697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4830092191696167},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21346956491470337},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.11753562092781067}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10384289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10384289","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6800000071525574}],"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":24,"referenced_works":["https://openalex.org/W565357261","https://openalex.org/W1646707810","https://openalex.org/W1964535365","https://openalex.org/W2040766536","https://openalex.org/W2111753883","https://openalex.org/W2158479468","https://openalex.org/W2160698719","https://openalex.org/W2169982856","https://openalex.org/W2170233819","https://openalex.org/W2605818517","https://openalex.org/W2789265722","https://openalex.org/W2973086798","https://openalex.org/W3011120880","https://openalex.org/W3099870866","https://openalex.org/W3183922633","https://openalex.org/W3210638057","https://openalex.org/W4205185654","https://openalex.org/W4211221179","https://openalex.org/W4309220322","https://openalex.org/W4315488689","https://openalex.org/W4383604498","https://openalex.org/W4386649063","https://openalex.org/W6743500281","https://openalex.org/W6845533454"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"The":[0,16,36,76,120,141,168],"paper":[1],"introduces":[2],"the":[3,43,63,66,71,93,116,132],"first":[4],"formulation":[5],"of":[6,24,27,33,42,79,115,134,149],"convex":[7,49,68,94],"Q-learning":[8,97],"for":[9,54,91,96],"Markov":[10],"decision":[11],"processes":[12],"with":[13,100,172],"function":[14],"approximation.":[15],"algorithms":[17,122],"and":[18,58,70,84,125,152],"theory":[19,169],"rest":[20],"on":[21],"a":[22,25,47,55,59,105,112,137,147,176],"relaxation":[23],"dual":[26],"Manne's":[28],"celebrated":[29],"linear":[30],"programming":[31,165],"characterization":[32],"optimal":[34],"control.":[35],"main":[37],"contributions":[38,80],"firstly":[39],"concern":[40,81],"properties":[41,99],"relaxation,":[44],"described":[45],"as":[46],"deterministic":[48],"program:":[50],"we":[51],"identify":[52],"conditions":[53],"bounded":[56,106],"solution,":[57],"significant":[60],"relationship":[61],"between":[62],"solution":[64,72,107],"to":[65,73,111,130,146,175],"new":[67,126],"program,":[69],"standard":[74],"Q-learning.":[75],"second":[77],"set":[78],"algorithm":[82],"design":[83],"analysis:":[85],"(i)":[86],"A":[87],"direct":[88],"model-free":[89],"method":[90],"approximating":[92],"program":[95],"shares":[98],"its":[101],"ideal.":[102],"In":[103],"particular,":[104],"is":[108,154,170],"ensured":[109],"subject":[110],"simple":[113],"property":[114],"basis":[117],"functions;":[118],"(ii)":[119],"proposed":[121],"are":[123,128],"convergent":[124],"techniques":[127],"introduced":[129],"obtain":[131],"rate":[133],"convergence":[135],"in":[136],"mean-square":[138],"sense;":[139],"(iii)":[140],"approach":[142],"can":[143,158],"be":[144,159],"generalized":[145],"range":[148],"performance":[150],"criteria,":[151],"it":[153],"found":[155],"that":[156],"variance":[157],"reduced":[160],"by":[161],"considering":[162],"\u201crelative\u201d":[163],"dynamic":[164],"equations;":[166],"(iv)":[167],"illustrated":[171],"an":[173],"application":[174],"classical":[177],"inventory":[178],"control":[179],"problem.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}