{"id":"https://openalex.org/W7128032002","doi":"https://doi.org/10.48550/arxiv.2602.05139","title":"Adaptive Exploration for Latent-State Bandits","display_name":"Adaptive Exploration for Latent-State Bandits","publication_year":2026,"publication_date":"2026-02-04","ids":{"openalex":"https://openalex.org/W7128032002","doi":"https://doi.org/10.48550/arxiv.2602.05139"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.05139","doi":"https://doi.org/10.48550/arxiv.2602.05139","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.05139","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"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.05139","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125147722","display_name":"Jikai Jin","orcid":"https://orcid.org/0009-0004-7988-4650","observed_orcids":["https://orcid.org/0009-0004-7988-4650"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jin, Jikai","raw_affiliation_strings":["The Institute for Computational and Mathematical Engineering Stanford University Stanford , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute for Computational and Mathematical Engineering Stanford University Stanford , CA , USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153520118","display_name":"Kenneth Hung","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hung, Kenneth","raw_affiliation_strings":["Ads","Online Experimentation Meta Platforms, Inc. Menlo Park , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ads","institution_ids":[]},{"raw_affiliation_string":"Online Experimentation Meta Platforms, Inc. Menlo Park , CA , USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109431491","display_name":"Sanath Kumar Krishnamurthy","orcid":"https://orcid.org/0009-0006-1197-5358","observed_orcids":["https://orcid.org/0009-0006-1197-5358"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krishnamurthy, Sanath Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125204007","display_name":"Baoyi Shi","orcid":"https://orcid.org/0009-0009-7362-0714","observed_orcids":["https://orcid.org/0009-0009-7362-0714"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shi, Baoyi","raw_affiliation_strings":["Central Applied Science Meta Platforms, Inc. Menlo Park , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central Applied Science Meta Platforms, Inc. Menlo Park , CA , USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091096255","display_name":"Congshan Zhang","orcid":"https://orcid.org/0009-0005-2815-7047","observed_orcids":["https://orcid.org/0009-0005-2815-7047"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Congshan","raw_affiliation_strings":["Ads","Online Experimentation Meta Platforms, Inc. Menlo Park , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ads","institution_ids":[]},{"raw_affiliation_string":"Online Experimentation Meta Platforms, Inc. Menlo Park , CA , USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"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":false,"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":1.0,"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":1.0,"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":0.0,"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/T12288","display_name":"Optimization and Search Problems","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/non-stationary-bandits","display_name":"non-stationary bandits","score":0.9049999713897705},{"id":"https://openalex.org/keywords/adaptive-exploration","display_name":"adaptive exploration","score":0.7099999785423279},{"id":"https://openalex.org/keywords/linucb","display_name":"LinUCB","score":0.8790000081062317},{"id":"https://openalex.org/keywords/dynamic-regret","display_name":"dynamic regret","score":0.7319999933242798}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7785000205039978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676800012588501},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.6259999871253967},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5702999830245972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328999757766724},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4878999888896942},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.43939998745918274},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.3386000096797943},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.314300000667572},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.05139","doi":"https://doi.org/10.48550/arxiv.2602.05139","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.05139","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.05139","doi":"https://doi.org/10.48550/arxiv.2602.05139","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.05139","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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/16","score":0.8053415417671204,"display_name":"Peace, justice, and strong institutions"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,33],"study":[1],"bandits":[2],"whose":[3],"rewards":[4,58],"depend":[5],"on":[6],"an":[7],"unobserved":[8],"Markov":[9],"state":[10,79,124],"that":[11,36],"evolves":[12],"independently":[13],"of":[14,42,59],"the":[15,25,43,66,100,114],"learner's":[16],"actions.":[17],"The":[18,62],"optimal":[19],"arm":[20],"can":[21],"change":[22],"even":[23],"though":[24],"learner":[26],"observes":[27],"only":[28],"past":[29],"actions":[30],"and":[31,71,84,95,104,110,123],"rewards.":[32],"propose":[34],"algorithms":[35],"feed":[37],"LinUCB":[38],"with":[39],"two":[40],"summaries":[41,101],"hidden":[44],"state:":[45],"a":[46,53],"lagged":[47],"action-reward":[48],"pair":[49],"and,":[50],"when":[51,99],"available,":[52],"probe":[54],"fingerprint":[55,67,119],"formed":[56],"from":[57],"multiple":[60],"arms.":[61],"adaptive":[63],"variants":[64],"refresh":[65],"using":[68],"residual,":[69],"margin,":[70],"staleness":[72],"tests.":[73],"In":[74],"synthetic":[75],"stress":[76],"tests":[77,112],"over":[78],"count,":[80],"transition":[81],"rate,":[82],"noise,":[83,122],"horizon,":[85],"these":[86],"methods":[87],"reduce":[88],"dynamic":[89],"regret":[90],"relative":[91],"to":[92],"standard,":[93],"adversarial,":[94],"non-stationary":[96],"bandit":[97],"baselines":[98],"distinguish":[102],"states":[103],"are":[105],"updated":[106],"often":[107],"enough.":[108],"Ablations":[109],"misspecification":[111],"identify":[113],"main":[115],"failure":[116],"modes:":[117],"weak":[118],"separation,":[120],"high":[121],"changes":[125],"during":[126],"sequential":[127],"probes.":[128]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2026-02-07T00:00:00"}