{"id":"https://openalex.org/W7223060104","doi":"https://doi.org/10.48550/arxiv.2610.24345","title":"The Certification Exponent: Instance-Optimal Sequential Certification of Policy Improvement from History Dependent Logs","display_name":"The Certification Exponent: Instance-Optimal Sequential Certification of Policy Improvement from History Dependent Logs","publication_year":2026,"publication_date":"2026-10-17","ids":{"openalex":"https://openalex.org/W7223060104","doi":"https://doi.org/10.48550/arxiv.2610.24345"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.24345","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.24345","pdf_url":"https://arxiv.org/pdf/2610.24345","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/2610.24345","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159108633","display_name":"Rui Wang*","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153468","display_name":"Microsoft (Canada)","ror":"https://ror.org/04xhxg104","country_code":"CA","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210153468"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Wang, Rui","raw_affiliation_strings":["Microsoft Vancouver , BC , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Vancouver , BC , Canada","institution_ids":["https://openalex.org/I4210153468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5159108633"],"corresponding_institution_ids":["https://openalex.org/I4210153468"],"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":0.9535999894142151,"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":0.9535999894142151,"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":0.03420000150799751,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0017999999690800905,"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/policy-improvement","display_name":"policy improvement","score":0.8489999771118164},{"id":"https://openalex.org/keywords/kullback-leibler-divergence","display_name":"Kullback-Leibler divergence","score":0.5630000233650208},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.45899999141693115}],"concepts":[{"id":"https://openalex.org/C46304622","wikidata":"https://www.wikidata.org/wiki/Q374814","display_name":"Certification","level":2,"score":0.7064999938011169},{"id":"https://openalex.org/C96865113","wikidata":"https://www.wikidata.org/wiki/Q2946816","display_name":"Certificate","level":2,"score":0.6377000212669373},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49480000138282776},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.450300008058548},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.40709999203681946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39489999413490295},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C125620115","wikidata":"https://www.wikidata.org/wiki/Q845249","display_name":"Logging","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.2639000117778778}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.24345","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.24345","pdf_url":"https://arxiv.org/pdf/2610.24345","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.2610.24345","doi":"https://doi.org/10.48550/arxiv.2610.24345","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.24345","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:2610.24345","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.24345","pdf_url":"https://arxiv.org/pdf/2610.24345","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223060104.pdf","grobid_xml":"https://content.openalex.org/works/W7223060104.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W4401608428","https://openalex.org/W4411707399","https://openalex.org/W4415084288","https://openalex.org/W7130678701","https://openalex.org/W7138884238","https://openalex.org/W7157990949","https://openalex.org/W7213511469","https://openalex.org/W7220676536"],"related_works":["https://openalex.org/W7213511469","https://openalex.org/W2899637793","https://openalex.org/W7222935813","https://openalex.org/W7172402300","https://openalex.org/W7216543892","https://openalex.org/W7202214405","https://openalex.org/W7220695213","https://openalex.org/W7215033316","https://openalex.org/W7133242746","https://openalex.org/W2330004501"],"abstract_inverted_index":{"Before":[0],"a":[1,5,11,27,68],"new":[2],"policy":[3,33],"replaces":[4],"deployed":[6],"one,":[7],"we":[8],"often":[9],"want":[10],"certificate,":[12],"computed":[13],"from":[14,63],"logged":[15,65,73],"episodes,":[16,92],"that":[17],"it":[18],"is":[19,34,55],"better.":[20],"We":[21],"ask":[22],"how":[23],"many":[24],"episodes":[25],"such":[26],"certificate":[28],"needs":[29],"when":[30],"the":[31,39,51,59,64,71,78],"logging":[32],"known":[35],"but":[36],"history-dependent,":[37],"and":[38,96],"error":[40],"probability":[41],"must":[42],"stay":[43],"below":[44],"$\u03b4$":[45],"in":[46,87],"every":[47],"environment":[48],"consistent":[49],"with":[50,70],"logs.":[52],"The":[53],"answer":[54],"an":[56],"exponent":[57],"$K^\\star$:":[58],"smallest":[60],"KL":[61],"divergence":[62],"law":[66,69],"to":[67],"same":[72],"action":[74],"probabilities":[75],"under":[76],"which":[77],"target":[79],"does":[80],"not":[81],"improve.":[82],"No":[83],"sound":[84],"certifier":[85],"stops":[86],"fewer":[88],"than":[89],"$\\log(1/\u03b4)/K^\\star$":[90],"expected":[91],"at":[93],"any":[94],"$\u03b4$,":[95],"whenever":[97],"$0":[98]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-21T00:00:00"}