{"id":"https://openalex.org/W4403443580","doi":"https://doi.org/10.48550/arxiv.2408.04526","title":"Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs","display_name":"Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs","publication_year":2024,"publication_date":"2024-08-08","ids":{"openalex":"https://openalex.org/W4403443580","doi":"https://doi.org/10.48550/arxiv.2408.04526"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2408.04526","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.04526","pdf_url":"https://arxiv.org/pdf/2408.04526","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,"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.04526","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043254593","display_name":"Kevin Tan","orcid":"https://orcid.org/0000-0001-5894-8839"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Kevin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074354165","display_name":"Wei Fan","orcid":"https://orcid.org/0000-0001-9815-710X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111283604","display_name":"Yuting Wei","orcid":"https://orcid.org/0000-0001-5432-712X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Yuting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9398999810218811,"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":0.9398999810218811,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7870357036590576},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6360065340995789},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6214284896850586},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.43683528900146484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3964923322200775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2935498356819153},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.18772074580192566},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.09896790981292725},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.06898406147956848},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.058035314083099365}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7870357036590576},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6360065340995789},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6214284896850586},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.43683528900146484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3964923322200775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2935498356819153},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.18772074580192566},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.09896790981292725},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.06898406147956848},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.058035314083099365}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2408.04526","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.04526","pdf_url":"https://arxiv.org/pdf/2408.04526","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,"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.2408.04526","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.04526","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,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.04526","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.04526","pdf_url":"https://arxiv.org/pdf/2408.04526","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,"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":[],"awards":[{"id":"https://openalex.org/G3024259446","display_name":"CAREER: Statistical Learning from a Modern Perspective: Over-parameterization, Regularization, and Generalization","funder_award_id":"2143215","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4167002044","display_name":"CIF: Small: Non-Asymptotic Foundations of Approximate Message Passing","funder_award_id":"2418156","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5174315691","display_name":"Collaborative Research: CIF: Medium: Statistical and Algorithmic Foundations of Efficient Reinforcement Learning","funder_award_id":"2106778","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403443580.pdf","grobid_xml":"https://content.openalex.org/works/W4403443580.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2607437843","https://openalex.org/W4295700147","https://openalex.org/W2963162727","https://openalex.org/W2877093712","https://openalex.org/W2116157560","https://openalex.org/W2106714532","https://openalex.org/W4297979791","https://openalex.org/W4310614650","https://openalex.org/W4386738330"],"abstract_inverted_index":{"Hybrid":[0],"Reinforcement":[1],"Learning":[2],"(RL),":[3],"where":[4],"an":[5,10,17,66],"agent":[6],"learns":[7],"from":[8],"both":[9,83,111],"offline":[11,48,100,148],"dataset":[12],"and":[13,49,88,102,113,139,156],"online":[14,51,157],"explorations":[15],"in":[16,46,72,99,147,165,194],"unknown":[18],"environment,":[19],"has":[20],"garnered":[21],"significant":[22],"recent":[23,97],"interest.":[24],"A":[25],"crucial":[26],"question":[27,71,79],"posed":[28],"by":[29],"Xie":[30],"et":[31,62],"al.":[32,63],"(2022)":[33],"is":[34],"whether":[35],"hybrid":[36,192],"RL":[37,52,76,86,101,115,149,158,193],"can":[38,140],"improve":[39,141],"upon":[40,96],"the":[41,56,73,78,84,89,143,173,176,185],"existing":[42],"lower":[43],"bounds":[44,133],"established":[45],"purely":[47,50],"without":[53,120],"relying":[54],"on":[55],"single-policy":[57,121],"concentrability":[58],"assumption.":[59],"While":[60],"Li":[61],"(2023)":[64],"provided":[65],"affirmative":[67],"answer":[68],"to":[69],"this":[70,93,182],"tabular":[74],"PAC":[75,112,154],"case,":[77],"remains":[80],"unsettled":[81],"for":[82,110,153,162,191],"regret-minimizing":[85,114,163],"case":[87],"non-tabular":[90],"case.":[91],"In":[92],"work,":[94],"building":[95],"advancements":[98],"reward-agnostic":[103],"exploration,":[104],"we":[105],"develop":[106],"computationally":[107],"efficient":[108],"algorithms":[109,127],"with":[116],"linear":[117,166,195],"function":[118],"approximation,":[119],"concentrability.":[122],"We":[123],"demonstrate":[124],"that":[125,134],"these":[126],"achieve":[128],"sharper":[129],"error":[130],"or":[131],"regret":[132],"are":[135],"no":[136],"worse":[137],"than,":[138],"on,":[142],"optimal":[144],"sample":[145],"complexity":[146],"(the":[150,159],"first":[151],"algorithm,":[152,161],"RL)":[155,164],"second":[160],"Markov":[167],"decision":[168],"processes":[169],"(MDPs),":[170],"regardless":[171],"of":[172,175],"quality":[174],"behavior":[177],"policy.":[178],"To":[179],"our":[180],"knowledge,":[181],"work":[183],"establishes":[184],"tightest":[186],"theoretical":[187],"guarantees":[188],"currently":[189],"available":[190],"MDPs.":[196]},"counts_by_year":[],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2025-10-10T00:00:00"}