{"id":"https://openalex.org/W4289655147","doi":"https://doi.org/10.1109/isit50566.2022.9834746","title":"Upper Confidence Interval Strategies for Multi-Armed Bandits with Entropy Rewards","display_name":"Upper Confidence Interval Strategies for Multi-Armed Bandits with Entropy Rewards","publication_year":2022,"publication_date":"2022-06-26","ids":{"openalex":"https://openalex.org/W4289655147","doi":"https://doi.org/10.1109/isit50566.2022.9834746"},"language":"en","primary_location":{"id":"doi:10.1109/isit50566.2022.9834746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834746","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","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/A5076051906","display_name":"Nir Weinberger","orcid":"https://orcid.org/0000-0001-6028-8892"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Nir Weinberger","raw_affiliation_strings":["Technion - Israel Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Technion - Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074718726","display_name":"Michal Yemini","orcid":"https://orcid.org/0000-0002-2087-1183"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michal Yemini","raw_affiliation_strings":["Princeton University"],"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076051906"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":0.7758,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66878307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1647","last_page":"1652"},"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/T10603","display_name":"Smart Grid Energy Management","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9898999929428101,"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/confidence-interval","display_name":"Confidence interval","score":0.5364341139793396},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5181228518486023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4996218681335449},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.4652698040008545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3235069811344147},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.315186083316803},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24880719184875488},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06634235382080078},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.060260117053985596}],"concepts":[{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.5364341139793396},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5181228518486023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4996218681335449},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.4652698040008545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3235069811344147},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.315186083316803},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24880719184875488},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06634235382080078},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.060260117053985596},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit50566.2022.9834746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834746","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","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":37,"referenced_works":["https://openalex.org/W148122774","https://openalex.org/W1661915592","https://openalex.org/W1819409771","https://openalex.org/W1989151402","https://openalex.org/W1989274820","https://openalex.org/W2008551287","https://openalex.org/W2009379494","https://openalex.org/W2009551863","https://openalex.org/W2048189453","https://openalex.org/W2049934117","https://openalex.org/W2058388580","https://openalex.org/W2101985079","https://openalex.org/W2106235393","https://openalex.org/W2108114251","https://openalex.org/W2114771311","https://openalex.org/W2124055802","https://openalex.org/W2134876548","https://openalex.org/W2141761557","https://openalex.org/W2142971854","https://openalex.org/W2148719904","https://openalex.org/W2168405694","https://openalex.org/W2542446008","https://openalex.org/W2554091414","https://openalex.org/W2603295249","https://openalex.org/W2763572636","https://openalex.org/W2963017284","https://openalex.org/W2963720577","https://openalex.org/W3045657706","https://openalex.org/W3102490990","https://openalex.org/W3102926694","https://openalex.org/W4205621617","https://openalex.org/W6606032028","https://openalex.org/W6637250909","https://openalex.org/W6676576766","https://openalex.org/W6678263215","https://openalex.org/W6680042586","https://openalex.org/W6729106829"],"related_works":["https://openalex.org/W2995364151","https://openalex.org/W797163146","https://openalex.org/W2068023914","https://openalex.org/W1899429405","https://openalex.org/W2401903608","https://openalex.org/W4221078923","https://openalex.org/W2066458123","https://openalex.org/W3005777437","https://openalex.org/W1578234703","https://openalex.org/W2084691705"],"abstract_inverted_index":{"We":[0,50,90],"introduce":[1],"a":[2,12,18],"multi-armed":[3],"bandit":[4],"problem":[5],"with":[6,42,86],"information-based":[7],"rewards.":[8],"At":[9],"each":[10,101],"round,":[11],"player":[13,33],"chooses":[14],"an":[15,22],"arm,":[16],"observes":[17],"symbol,":[19],"and":[20,105],"receives":[21],"unobserved":[23],"reward":[24,40],"in":[25,71],"the":[26,29,37,43,47,68,72,97,103,111,121,124],"form":[27],"of":[28,46,100,102,123],"symbol\u2019s":[30],"self-information.":[31],"The":[32,63,75],"aims":[34],"to":[35,84,110],"maximize":[36],"expected":[38,98],"total":[39],"associated":[41],"entropy":[44,73,88],"values":[45],"arms":[48],"played.":[49],"propose":[51],"two":[52],"algorithms":[53,125],"based":[54],"on":[55,79],"upper":[56,95],"confidence":[57],"bounds":[58],"(UCB)":[59],"for":[60],"this":[61],"model.":[62],"first":[64],"algorithm":[65,77],"optimistically":[66],"corrects":[67],"bias":[69],"term":[70],"estimation.":[74],"second":[76],"relies":[78],"data-dependent":[80],"UCBs":[81],"that":[82],"adapt":[83],"sources":[85],"small":[87],"values.":[89],"provide":[91,117],"performance":[92],"guarantees":[93],"by":[94],"bounding":[96],"regret":[99,122],"algorithms,":[104],"compare":[106],"their":[107],"asymptotic":[108],"behavior":[109],"Lai-Robbins":[112],"lower":[113],"bound.":[114],"Finally,":[115],"we":[116],"numerical":[118],"results":[119],"illustrating":[120],"presented.":[126]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}