{"id":"https://openalex.org/W4385338399","doi":"https://doi.org/10.1109/tit.2023.3299460","title":"Multi-Armed Bandits With Self-Information Rewards","display_name":"Multi-Armed Bandits With Self-Information Rewards","publication_year":2023,"publication_date":"2023-07-28","ids":{"openalex":"https://openalex.org/W4385338399","doi":"https://doi.org/10.1109/tit.2023.3299460"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2023.3299460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2023.3299460","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-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":["Faculty of Electrical and Computer Engineering, Technion—Israel Institute of Technology, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical and Computer Engineering, Technion—Israel Institute of Technology, Haifa, Israel","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/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Michal Yemini","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilan University, Ramat Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"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":1.0189,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78469277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"69","issue":"11","first_page":"7160","last_page":"7184"},"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":0.993399977684021,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9865000247955322,"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":0.8786050081253052},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.6585097312927246},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5887923836708069},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5828337669372559},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5066285729408264},{"id":"https://openalex.org/keywords/bernoullis-principle","display_name":"Bernoulli's principle","score":0.5055990219116211},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46493667364120483},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.45851564407348633},{"id":"https://openalex.org/keywords/alphabet","display_name":"Alphabet","score":0.45079779624938965},{"id":"https://openalex.org/keywords/online-algorithm","display_name":"Online algorithm","score":0.4463749825954437},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4417969584465027},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3543276786804199},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20998087525367737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18952199816703796}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8786050081253052},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.6585097312927246},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5887923836708069},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5828337669372559},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5066285729408264},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.5055990219116211},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46493667364120483},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.45851564407348633},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.45079779624938965},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.4463749825954437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4417969584465027},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3543276786804199},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20998087525367737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18952199816703796},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tit.2023.3299460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2023.3299460","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5013039200","display_name":null,"funder_award_id":"1782/22","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W50486269","https://openalex.org/W148122774","https://openalex.org/W638603679","https://openalex.org/W1501823362","https://openalex.org/W1661915592","https://openalex.org/W1662803991","https://openalex.org/W1699297496","https://openalex.org/W1819409771","https://openalex.org/W1984332158","https://openalex.org/W1989151402","https://openalex.org/W1989274820","https://openalex.org/W1998017597","https://openalex.org/W1999277453","https://openalex.org/W2008551287","https://openalex.org/W2009379494","https://openalex.org/W2009551863","https://openalex.org/W2039522160","https://openalex.org/W2048189453","https://openalex.org/W2058388580","https://openalex.org/W2061753713","https://openalex.org/W2077148472","https://openalex.org/W2101985079","https://openalex.org/W2106164082","https://openalex.org/W2106235393","https://openalex.org/W2108114251","https://openalex.org/W2114771311","https://openalex.org/W2119738618","https://openalex.org/W2124055802","https://openalex.org/W2134876548","https://openalex.org/W2140010215","https://openalex.org/W2141761557","https://openalex.org/W2142971854","https://openalex.org/W2144679335","https://openalex.org/W2148719904","https://openalex.org/W2151376060","https://openalex.org/W2168405694","https://openalex.org/W2257317309","https://openalex.org/W2397735741","https://openalex.org/W2478708596","https://openalex.org/W2542446008","https://openalex.org/W2603295249","https://openalex.org/W2763572636","https://openalex.org/W2772950549","https://openalex.org/W2787284768","https://openalex.org/W2887271511","https://openalex.org/W2946964102","https://openalex.org/W2950929549","https://openalex.org/W2962901934","https://openalex.org/W2963017284","https://openalex.org/W2963720577","https://openalex.org/W2985072977","https://openalex.org/W3006305332","https://openalex.org/W3020125231","https://openalex.org/W3045657706","https://openalex.org/W3089716481","https://openalex.org/W3100329718","https://openalex.org/W3102223710","https://openalex.org/W3102490990","https://openalex.org/W3102926694","https://openalex.org/W3124527634","https://openalex.org/W3154224757","https://openalex.org/W3175476058","https://openalex.org/W4206275166","https://openalex.org/W4225285064","https://openalex.org/W4232620022","https://openalex.org/W4289655147","https://openalex.org/W4293404332","https://openalex.org/W4302366875","https://openalex.org/W4362736692","https://openalex.org/W6602031475","https://openalex.org/W6606032028","https://openalex.org/W6620592660","https://openalex.org/W6630117878","https://openalex.org/W6633965395","https://openalex.org/W6637077600","https://openalex.org/W6637250909","https://openalex.org/W6637495066","https://openalex.org/W6639039794","https://openalex.org/W6675656252","https://openalex.org/W6676576766","https://openalex.org/W6678263215","https://openalex.org/W6680042586","https://openalex.org/W6729106829","https://openalex.org/W6747994166","https://openalex.org/W6752838982","https://openalex.org/W6763452204","https://openalex.org/W6785377095","https://openalex.org/W6789638599"],"related_works":["https://openalex.org/W4376155396","https://openalex.org/W2971351794","https://openalex.org/W1947085858","https://openalex.org/W2101991911","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W3123835761","https://openalex.org/W118270247"],"abstract_inverted_index":{"This":[0],"paper":[1,227],"introduces":[2],"the":[3,28,31,35,42,46,51,62,68,72,76,79,90,95,98,107,111,137,143,147,150,159,164,169,172,180,197,202,206,218,222,226],"informational":[4],"multi-armed":[5],"bandit":[6],"(IMAB)":[7],"model,":[8],"in":[9,27,110,146,195,210,225],"which":[10,93,196],"at":[11],"each":[12,141],"round,":[13],"a":[14,20,184,190,211],"player":[15,58,181,198],"chooses":[16],"an":[17,24,39],"arm,":[18],"observes":[19],"symbol,":[21],"and":[22,178],"receives":[23],"unobserved":[25],"reward":[26,37,65],"form":[29],"of":[30,38,45,50,71,97,140,142,153,221],"symbol\u2019s":[32],"self-information.":[33],"Thus,":[34],"expected":[36,63,138,219],"arm":[40],"is":[41,82,156,176,193],"Shannon":[43],"entropy":[44,69,100,112,128],"probability":[47],"mass":[48],"function":[49],"source":[52],"that":[53,78,122,171],"generates":[54],"its":[55],"symbols.":[56],"The":[57,102,114],"aims":[59,199],"to":[60,124,158,200],"maximize":[61],"total":[64],"associated":[66],"with":[67,126],"values":[70],"arms":[73],"played.":[74],"Under":[75],"assumption":[77,170],"alphabet":[80,174,208],"size":[81,175,209],"known,":[83],"two":[84],"UCB-based":[85,191],"algorithms":[86,155,223],"are":[87,132,228],"proposed":[88],"for":[89,163],"IMAB":[91],"model":[92],"consider":[94],"biases":[96],"plug-in":[99],"estimator.":[101],"first":[103],"algorithm":[104,116,192],"optimistically":[105],"corrects":[106],"bias":[108],"term":[109],"estimation.":[113],"second":[115],"relies":[117],"on":[118,188],"data-dependent":[119],"confidence":[120],"intervals":[121],"adapt":[123],"sources":[125],"small":[127],"values.":[129],"Performance":[130],"guarantees":[131],"provided":[133],"by":[134,205],"upper":[135,186],"bounding":[136],"regret":[139,203,220],"algorithms.":[144],"Furthermore,":[145],"Bernoulli":[148],"case,":[149],"asymptotic":[151],"behavior":[152],"these":[154],"compared":[157],"Lai-Robbins":[160],"lower":[161],"bound":[162,187],"pseudo":[165],"regret.":[166],"Additionally,":[167],"under":[168],"exact":[173],"unknown,":[177],"instead":[179],"only":[182],"knows":[183],"loose":[185],"it,":[189],"proposed,":[194],"reduce":[201],"caused":[204],"unknown":[207],"finite":[212],"time":[213],"regime.":[214],"Numerical":[215],"results":[216],"illustrating":[217],"presented":[224],"provided.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}