{"id":"https://openalex.org/W7220683973","doi":"https://doi.org/10.48550/arxiv.2610.04752","title":"Variance-Aware Fine-Grained Gap-Dependent Bounds for Online Reinforcement Learning","display_name":"Variance-Aware Fine-Grained Gap-Dependent Bounds for Online Reinforcement Learning","publication_year":2026,"publication_date":"2026-10-03","ids":{"openalex":"https://openalex.org/W7220683973","doi":"https://doi.org/10.48550/arxiv.2610.04752"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.04752","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04752","pdf_url":"https://arxiv.org/pdf/2610.04752","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.04752","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157670484","display_name":"Haochen Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Haochen","raw_affiliation_strings":["Department of Statistics , The Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics , The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089400160","display_name":"Lingzhou Xue","orcid":"https://orcid.org/0000-0002-8252-0637","observed_orcids":["https://orcid.org/0000-0002-8252-0637"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xue, Lingzhou","raw_affiliation_strings":["Department of Statistics , The Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics , The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157785094","display_name":"Zhong Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng, Zhong","raw_affiliation_strings":["Department of Applied and Computational Mathematics and Statistics , University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied and Computational Mathematics and Statistics , University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.8647000193595886,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.8647000193595886,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1348000019788742,"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/T12072","display_name":"Machine Learning and Algorithms","score":9.999999747378752e-05,"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/online-reinforcement-learning","display_name":"online reinforcement learning","score":0.9800000190734863},{"id":"https://openalex.org/keywords/model-free-reinforcement-learning","display_name":"model-free reinforcement learning","score":0.7960000038146973},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.5540000200271606}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9585999846458435},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7099999785423279},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6775000095367432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6237999796867371},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5042999982833862},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46639999747276306},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4438999891281128},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3352999985218048},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.04752","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04752","pdf_url":"https://arxiv.org/pdf/2610.04752","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.04752","doi":"https://doi.org/10.48550/arxiv.2610.04752","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.04752","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.04752","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04752","pdf_url":"https://arxiv.org/pdf/2610.04752","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220683973.pdf","grobid_xml":"https://content.openalex.org/works/W7220683973.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W3119494765","https://openalex.org/W7131431141","https://openalex.org/W7206173067"],"related_works":["https://openalex.org/W4415316306","https://openalex.org/W2947782105","https://openalex.org/W4411143006","https://openalex.org/W4403364517","https://openalex.org/W7140396214","https://openalex.org/W4318904321","https://openalex.org/W3104032756","https://openalex.org/W4417118614","https://openalex.org/W2945119207","https://openalex.org/W3206149081"],"abstract_inverted_index":{"We":[0],"study":[1],"model-free":[2,30,40,81],"online":[3,82],"reinforcement":[4],"learning":[5],"(RL)":[6],"for":[7,29,39,73,119],"episodic":[8],"tabular":[9],"Markov":[10],"decision":[11],"processes,":[12],"focusing":[13],"on":[14],"both":[15,120,142],"gap-dependent":[16,24,54,69,105],"regret":[17,70,121,143],"and":[18,52,96,122,144],"policy":[19,89],"switching":[20,107,124,146],"cost.":[21,147],"While":[22],"fine-grained":[23,68,94],"analysis":[25,114],"has":[26],"been":[27],"established":[28],"RL":[31],"algorithms":[32,41],"using":[33,97],"Hoeffding-type":[34],"exploration":[35,44],"bonuses,":[36,100],"such":[37],"results":[38],"with":[42],"variance-based":[43,99],"bonuses":[45],"remain":[46],"unknown,":[47],"despite":[48],"their":[49],"superior":[50],"worst-case":[51,117],"coarse-grained":[53],"guarantees.":[55],"In":[56,111],"this":[57,61],"paper,":[58],"we":[59,101],"resolve":[60],"open":[62],"problem":[63],"by":[64,85],"establishing":[65],"the":[66,103,127],"first":[67],"upper":[71],"bound":[72],"UCB-Bernstein+,":[74],"a":[75,87],"refined":[76,98],"UCB-Bernstein":[77,129],"algorithm,":[78],"in":[79,141],"variance-aware":[80],"RL.":[83],"Moreover,":[84],"integrating":[86],"stage-wise":[88],"update":[90],"design":[91],"into":[92],"our":[93,113],"framework":[95],"achieve":[102],"best-known":[104],"local":[106,123,145],"cost":[108,125],"to":[109],"date.":[110],"addition,":[112],"yields":[115],"improved":[116],"guarantees":[118],"over":[126],"original":[128],"algorithm.":[130],"Numerical":[131],"experiments":[132],"further":[133],"demonstrate":[134],"that":[135],"UCB-Bernstein+":[136],"achieves":[137],"favorable":[138],"empirical":[139],"performance":[140]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-07T00:00:00"}