{"id":"https://openalex.org/W4407950958","doi":"https://doi.org/10.1109/cdc56724.2024.10886530","title":"Finite-Time Error Analysis of Soft Q-Learning: Switching System Approach","display_name":"Finite-Time Error Analysis of Soft Q-Learning: Switching System Approach","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407950958","doi":"https://doi.org/10.1109/cdc56724.2024.10886530"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10886530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd 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/A5116424644","display_name":"Narim Jeong","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Narim Jeong","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),Department of Electrical Engineering,Daejeon,South Korea,34141"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),Department of Electrical Engineering,Daejeon,South Korea,34141","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108315551","display_name":"Donghwan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Donghwan Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),Department of Electrical Engineering,Daejeon,South Korea,34141"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),Department of Electrical Engineering,Daejeon,South Korea,34141","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5116424644"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25585731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3897","last_page":"3904"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9531000256538391,"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/T12676","display_name":"Machine Learning and ELM","score":0.9531000256538391,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5254808068275452},{"id":"https://openalex.org/keywords/error-analysis","display_name":"Error analysis","score":0.466103196144104},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2898852229118347},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.20919358730316162}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5254808068275452},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.466103196144104},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2898852229118347},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.20919358730316162}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10886530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1552094772","https://openalex.org/W1999254175","https://openalex.org/W2071983464","https://openalex.org/W2077343054","https://openalex.org/W2118686230","https://openalex.org/W2165131254","https://openalex.org/W4241157193","https://openalex.org/W4382064684","https://openalex.org/W4390938885","https://openalex.org/W6638018090","https://openalex.org/W6734206676","https://openalex.org/W6734517396","https://openalex.org/W6736495777","https://openalex.org/W6738370996","https://openalex.org/W6739455066","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6752164047","https://openalex.org/W6759637383","https://openalex.org/W6759918608","https://openalex.org/W6763048320","https://openalex.org/W6768147998","https://openalex.org/W6773637655","https://openalex.org/W6776724963","https://openalex.org/W6802333366","https://openalex.org/W6803036901"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Soft":[0],"Q-learning":[1,6,38,55,64,93,107],"is":[2],"a":[3,46],"variation":[4],"of":[5,36,53,62,105,128],"designed":[7],"to":[8,19,39,44],"solve":[9],"entropy":[10,22],"regularized":[11,23],"Markov":[12],"decision":[13],"problems":[14],"where":[15],"an":[16],"agent":[17],"aims":[18,43],"maximize":[20],"the":[21,68,72,75,102,119,125],"value":[24],"function.":[25],"Despite":[26],"its":[27],"empirical":[28],"success,":[29],"there":[30],"have":[31],"been":[32],"limited":[33],"theoretical":[34],"studies":[35],"soft":[37,54,63,92,106],"date.":[40],"This":[41],"paper":[42],"offer":[45],"novel":[47,86],"and":[48,71,115],"unified":[49],"finite-time,":[50],"control-theoretic":[51],"analysis":[52,99,127],"algorithms.":[56,94,132],"We":[57,95],"focus":[58],"on":[59],"two":[60],"types":[61],"algorithms:":[65],"one":[66],"utilizing":[67],"log-sum-exp":[69],"operator":[70],"other":[73,129],"employing":[74],"Boltzmann":[76],"operator.":[77],"By":[78],"using":[79],"dynamical":[80],"switching":[81,112],"system":[82,113],"models,":[83],"we":[84],"derive":[85],"finite-time":[87,126],"error":[88],"bounds":[89],"for":[90,121],"both":[91],"hope":[96],"that":[97],"our":[98],"will":[100],"deepen":[101],"current":[103],"understanding":[104],"by":[108],"establishing":[109],"connections":[110],"with":[111],"models":[114],"may":[116],"even":[117],"pave":[118],"way":[120],"new":[122],"frameworks":[123],"in":[124],"reinforcement":[130],"learning":[131]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}