{"id":"https://openalex.org/W4411143006","doi":"https://doi.org/10.1109/access.2025.3577997","title":"Variation-Aware Bernstein-Based Upper Confidence Reinforcement Learning for Environment With Endogenous and Exogenous Uncertainty","display_name":"Variation-Aware Bernstein-Based Upper Confidence Reinforcement Learning for Environment With Endogenous and Exogenous Uncertainty","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411143006","doi":"https://doi.org/10.1109/access.2025.3577997"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3577997","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3577997","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3577997","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048942753","display_name":"Ruoqi Wen","orcid":"https://orcid.org/0000-0002-7414-5638"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruoqi Wen","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7414-5638","affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014842979","display_name":"Rongpeng Li","orcid":"https://orcid.org/0000-0003-4297-5060"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongpeng Li","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4297-5060","affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04885907,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"100889","last_page":"100903"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9955000281333923,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7105547189712524},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.6766656041145325},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6228445172309875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40224742889404297}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7105547189712524},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.6766656041145325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6228445172309875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40224742889404297},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3577997","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3577997","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ce1598939af44c7b81840dea53244a6a","is_oa":true,"landing_page_url":"https://doaj.org/article/ce1598939af44c7b81840dea53244a6a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 100889-100903 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3577997","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3577997","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.6299999952316284,"display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G4802220448","display_name":null,"funder_award_id":"BDIC-2023-B-001","funder_id":"https://openalex.org/F4320322687","funder_display_name":"Chongqing University of Posts and Telecommunications"},{"id":"https://openalex.org/G7705622201","display_name":null,"funder_award_id":"LR23F010005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322687","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2009551863","https://openalex.org/W2142971854","https://openalex.org/W2290051315","https://openalex.org/W2489939061","https://openalex.org/W2972710806","https://openalex.org/W2993208870","https://openalex.org/W3020125231","https://openalex.org/W3115949757","https://openalex.org/W3121822496","https://openalex.org/W3133735442","https://openalex.org/W4213251304","https://openalex.org/W4214717370","https://openalex.org/W4221140173","https://openalex.org/W4226507192","https://openalex.org/W4245577611","https://openalex.org/W4287725108","https://openalex.org/W4294741352","https://openalex.org/W4389065290","https://openalex.org/W4392931579","https://openalex.org/W4393198079","https://openalex.org/W4402128007","https://openalex.org/W4407129397","https://openalex.org/W4408029954","https://openalex.org/W6637077600","https://openalex.org/W6639039794","https://openalex.org/W6762473756","https://openalex.org/W6764339584","https://openalex.org/W6767544959","https://openalex.org/W6771332416","https://openalex.org/W6776719514","https://openalex.org/W6779771741","https://openalex.org/W6780275439","https://openalex.org/W6790330943","https://openalex.org/W6809629233","https://openalex.org/W6810936331","https://openalex.org/W6877599082"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2386430105","https://openalex.org/W2356521405","https://openalex.org/W2038534795","https://openalex.org/W2384358604","https://openalex.org/W1567829292","https://openalex.org/W3001063351","https://openalex.org/W3196905815"],"abstract_inverted_index":{"Online":[0],"Reinforcement":[1,87],"Learning":[2,88],"(RL)":[3],"has":[4,56],"yielded":[5],"remarkable":[6],"performance":[7],"in":[8,35,128,166],"dynamic":[9],"wireless":[10],"communication":[11],"and":[12,19,46,73,80,111,114,143],"networks":[13],"by":[14],"interacting":[15],"with":[16,53,70,124],"the":[17,22,41,105,125,129,134,137,141,146,163,167],"environment":[18,38],"gradually":[20],"improving":[21],"effectiveness":[23],"of":[24,44,119,136,140,149],"its":[25],"policy.":[26],"As":[27],"it":[28],"is":[29],"normal":[30],"to":[31,40,98,108],"witness":[32],"much":[33],"uncertainty":[34,113],"such":[36],"an":[37],"due":[39,107],"intrinsic":[42],"randomness":[43],"channels":[45],"service":[47],"demands,":[48],"designing":[49],"a":[50,78,82,99,116],"sample-efficient":[51],"RL":[52],"bounded":[54],"regrets":[55],"significant":[57],"merits.":[58],"In":[59,90],"this":[60],"paper,":[61],"we":[62,92,153],"focus":[63],"on":[64],"general":[65],"Markov":[66],"Decision":[67],"Processes":[68],"(MDPs)":[69],"time-evolving":[71],"rewards":[72],"state":[74,138],"transition":[75],"probability":[76],"unknown":[77],"priori":[79],"develop":[81],"Variation-aware":[83],"Bernstein-based":[84],"Upper":[85],"Confidence":[86],"(VB-UCRL).":[89],"particular,":[91],"allow":[93],"for":[94],"restarting":[95],"VB-UCRL":[96,160],"according":[97],"variation-aware":[100],"schedule.":[101],"We":[102],"successfully":[103],"overcome":[104],"challenges":[106],"both":[109],"endogenous":[110],"exogenous":[112],"establish":[115],"regret":[117],"bound":[118],"saving":[120],"at":[121],"most":[122],"\u221aSorS1/6T1/12compared":[123],"latest":[126],"results":[127],"literature,":[130],"where":[131],"S":[132],"denotes":[133],"size":[135],"space":[139],"MDP":[142],"T":[144],"indicates":[145],"iteration":[147],"index":[148],"learning":[150],"time-steps.":[151],"Finally,":[152],"show":[154],"via":[155],"simulation":[156],"that":[157],"our":[158],"algorithm":[159],"significantly":[161],"outperforms":[162],"existing":[164],"algorithms":[165],"literature.":[168]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}