{"id":"https://openalex.org/W4415524532","doi":"https://doi.org/10.1109/mlsp62443.2025.11204293","title":"Learning from Multiple Noisily Optimal Demonstrators in Stochastic Multi Armed Bandits","display_name":"Learning from Multiple Noisily Optimal Demonstrators in Stochastic Multi Armed Bandits","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524532","doi":"https://doi.org/10.1109/mlsp62443.2025.11204293"},"language":null,"primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100422627","display_name":"Hongyu Wang","orcid":"https://orcid.org/0000-0001-5475-579X"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hongyu Wang","raw_affiliation_strings":["Michigan State University,Electrical Computer Engineering Department,East Lansing,MI,USA,48824"],"affiliations":[{"raw_affiliation_string":"Michigan State University,Electrical Computer Engineering Department,East Lansing,MI,USA,48824","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005271216","display_name":"Panagiotis A. Traganitis","orcid":"https://orcid.org/0000-0002-5420-758X"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panagiotis A. Traganitis","raw_affiliation_strings":["Michigan State University,Electrical Computer Engineering Department,East Lansing,MI,USA,48824"],"affiliations":[{"raw_affiliation_string":"Michigan State University,Electrical Computer Engineering Department,East Lansing,MI,USA,48824","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100422627"],"corresponding_institution_ids":["https://openalex.org/I87216513"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17006242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9976999759674072,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9976999759674072,"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":0.9972000122070312,"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":0.9894000291824341,"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/regret","display_name":"Regret","score":0.7657999992370605},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.5317999720573425},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.39250001311302185},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3296000063419342},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.29660001397132874},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.27410000562667847}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7657999992370605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6313999891281128},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.5317999720573425},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5170000195503235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48570001125335693},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3734999895095825},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2630999982357025},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W1988790447","https://openalex.org/W2009551863","https://openalex.org/W2077902449","https://openalex.org/W2150638405","https://openalex.org/W2499002200","https://openalex.org/W2884765233","https://openalex.org/W2950929549","https://openalex.org/W2962849870","https://openalex.org/W3200108882","https://openalex.org/W4206275166","https://openalex.org/W4206530644","https://openalex.org/W4404442983"],"related_works":[],"abstract_inverted_index":{"The":[0],"classical":[1],"Multi-armed":[2],"Bandit":[3],"(MAB)":[4],"framework":[5],"relies":[6],"on":[7],"immediate":[8],"access":[9],"to":[10,31],"reward":[11,35,68],"feedback,":[12],"yet":[13],"in":[14,59,64],"many":[15],"practical":[16],"settings":[17],"rewards":[18],"are":[19,94],"inaccessible":[20],"or":[21,43],"severely":[22],"delayed.":[23],"To":[24],"address":[25],"this":[26,47],"gap,":[27],"inverse":[28],"MAB":[29,62],"seeks":[30],"recover":[32],"the":[33,39,51,65,83],"latent":[34],"function":[36],"by":[37],"observing":[38],"actions":[40],"of":[41,53,67],"one":[42,92,102],"more":[44],"demonstrators.":[45],"In":[46],"work,":[48],"we":[49],"study":[50],"problem":[52],"learning":[54,73],"from":[55,74,98],"multiple":[56],"noisy":[57],"demonstrations":[58],"a":[60,90],"stochastic":[61],"environment,":[63],"absence":[66],"information.":[69],"Four":[70],"algorithms":[71],"for":[72],"noisily":[75],"optimal":[76,84],"demonstrators,":[77],"that":[78],"is,":[79],"demonstrators":[80],"who":[81],"choose":[82],"arm":[85],"with":[86],"fixed":[87],"probability":[88],"and":[89,101,114],"suboptimal":[91],"otherwise,":[93],"considered;":[95],"three":[96],"adapted":[97],"existing":[99],"literature":[100],"newly":[103],"proposed.":[104],"Their":[105],"performance":[106],"is":[107],"evaluated":[108],"both":[109],"theoretically,":[110],"through":[111],"regret":[112],"bounds,":[113],"empirically,":[115],"via":[116],"numerical":[117],"tests.":[118]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}