{"id":"https://openalex.org/W4408399710","doi":"https://doi.org/10.1109/lcsys.2025.3551265","title":"A Weighted Smooth Q-Learning Algorithm","display_name":"A Weighted Smooth Q-Learning Algorithm","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408399710","doi":"https://doi.org/10.1109/lcsys.2025.3551265"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2025.3551265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2025.3551265","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Control Systems Letters","raw_type":"journal-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/A5100029839","display_name":"Antony Vijesh","orcid":"https://orcid.org/0000-0003-2435-9774"},"institutions":[{"id":"https://openalex.org/I64295750","display_name":"Indian Institute of Technology Indore","ror":"https://ror.org/01hhf7w52","country_code":"IN","type":"education","lineage":["https://openalex.org/I64295750"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"V. Antony Vijesh","raw_affiliation_strings":["Department of Mathematics, Indian Institute of Technology Indore, Indore, India","Department of Mathematics, Indian Institute of Technology (IIT), Indore, India"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Indian Institute of Technology Indore, Indore, India","institution_ids":["https://openalex.org/I64295750"]},{"raw_affiliation_string":"Department of Mathematics, Indian Institute of Technology (IIT), Indore, India","institution_ids":["https://openalex.org/I64295750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100029840","display_name":"S R Shreyas","orcid":null},"institutions":[{"id":"https://openalex.org/I64295750","display_name":"Indian Institute of Technology Indore","ror":"https://ror.org/01hhf7w52","country_code":"IN","type":"education","lineage":["https://openalex.org/I64295750"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. R. Shreyas","raw_affiliation_strings":["Department of Mathematics, Indian Institute of Technology Indore, Indore, India","Department of Mathematics, Indian Institute of Technology (IIT), Indore, India"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Indian Institute of Technology Indore, Indore, India","institution_ids":["https://openalex.org/I64295750"]},{"raw_affiliation_string":"Department of Mathematics, Indian Institute of Technology (IIT), Indore, India","institution_ids":["https://openalex.org/I64295750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100029839"],"corresponding_institution_ids":["https://openalex.org/I64295750"],"apc_list":null,"apc_paid":null,"fwci":1.2656,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76423198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"9","issue":null,"first_page":"21","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13717","display_name":"Advanced Algorithms and Applications","score":0.8306000232696533,"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/T13717","display_name":"Advanced Algorithms and Applications","score":0.8306000232696533,"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/T10057","display_name":"Face and Expression Recognition","score":0.7982000112533569,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.7727000117301941,"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":0.4872385561466217},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.48544842004776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42596733570098877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4872385561466217},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48544842004776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42596733570098877}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcsys.2025.3551265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2025.3551265","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Control Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W173318062","https://openalex.org/W2077343054","https://openalex.org/W2165131254","https://openalex.org/W2941439130","https://openalex.org/W2949350092","https://openalex.org/W3004059350","https://openalex.org/W3174772619","https://openalex.org/W3199561448","https://openalex.org/W4233696721","https://openalex.org/W4243772471","https://openalex.org/W4297964528","https://openalex.org/W4367298527","https://openalex.org/W6677067356","https://openalex.org/W6713603661","https://openalex.org/W6734206676","https://openalex.org/W6734517396","https://openalex.org/W6739455066","https://openalex.org/W6741813938","https://openalex.org/W6752164047","https://openalex.org/W6759918608","https://openalex.org/W6762358693","https://openalex.org/W6771936881","https://openalex.org/W6775686901","https://openalex.org/W6784003830","https://openalex.org/W6785865125","https://openalex.org/W6785894376"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Q-learning":[0,3,12,19,34,109],"and":[1,48,67],"double":[2,18],"are":[4,95],"well-known":[5],"sample-based,":[6],"off-policy":[7],"reinforcement":[8],"learning":[9],"algorithms.":[10],"However,":[11],"suffers":[13,20],"from":[14,21],"overestimation":[15],"bias,":[16],"while":[17],"underestimation":[22],"bias.":[23],"To":[24],"address":[25],"these":[26],"issues,":[27],"this":[28],"letter":[29],"proposes":[30],"a":[31,41,59,69,82],"weighted":[32,42,107],"smooth":[33,108],"(WSQL)":[35],"algorithm.":[36,110],"The":[37],"proposed":[38,77,106],"algorithm":[39,90],"employs":[40],"combination":[43],"of":[44,54,75,88,104],"the":[45,49,55,71,76,86,102,105],"mellowmax":[46],"operator":[47,51],"log-sum-exp":[50],"in":[52],"place":[53],"maximum":[56],"operator.":[57],"Firstly,":[58],"new":[60],"stochastic":[61],"approximation":[62],"based":[63],"result":[64],"is":[65,79,91],"derived":[66],"as":[68],"consequence":[70],"almost":[72],"sure":[73],"convergence":[74],"WSQL":[78,89],"presented.":[80],"Further,":[81],"sufficient":[83],"condition":[84],"for":[85],"boundedness":[87],"obtained.":[92],"Numerical":[93],"experiments":[94],"conducted":[96],"on":[97],"benchmark":[98],"examples":[99],"to":[100],"validate":[101],"effectiveness":[103]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-03-14T00:00:00"}