{"id":"https://openalex.org/W2910458483","doi":"https://doi.org/10.1145/3305218.3305252","title":"Observe Before Play","display_name":"Observe Before Play","publication_year":2019,"publication_date":"2019-01-17","ids":{"openalex":"https://openalex.org/W2910458483","doi":"https://doi.org/10.1145/3305218.3305252","mag":"2910458483"},"language":"en","primary_location":{"id":"doi:10.1145/3305218.3305252","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3305218.3305252","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","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/A5085050673","display_name":"Jinhang Zuo","orcid":"https://orcid.org/0000-0002-9557-3551"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jinhang Zuo","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763625","display_name":"Xiaoxi Zhang","orcid":"https://orcid.org/0000-0003-0751-2773"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoxi Zhang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085243096","display_name":"Carlee Joe\u2010Wong","orcid":"https://orcid.org/0000-0003-0785-9291"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlee Joe-Wong","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085050673"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.9903,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.77975593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"46","issue":"2","first_page":"89","last_page":"90"},"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":0.9732000231742859,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9715999960899353,"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":0.906496524810791},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.5545830726623535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5535305142402649},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5437028408050537},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.5361926555633545},{"id":"https://openalex.org/keywords/bernoullis-principle","display_name":"Bernoulli's principle","score":0.525439441204071},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4928617477416992},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4590076804161072},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.33273035287857056},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.3296273350715637},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3263680934906006},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12266772985458374},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08271464705467224}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.906496524810791},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.5545830726623535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5535305142402649},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5437028408050537},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.5361926555633545},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.525439441204071},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4928617477416992},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4590076804161072},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.33273035287857056},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3296273350715637},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3263680934906006},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12266772985458374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08271464705467224},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3305218.3305252","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3305218.3305252","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2950929549","https://openalex.org/W2997266031"],"related_works":["https://openalex.org/W2962949156","https://openalex.org/W4289341771","https://openalex.org/W3114769327","https://openalex.org/W3191284239","https://openalex.org/W2996787464","https://openalex.org/W2958076322","https://openalex.org/W2964268945","https://openalex.org/W2619553246","https://openalex.org/W4294988689","https://openalex.org/W3174419385"],"abstract_inverted_index":{"We":[0,91],"consider":[1],"the":[2,33,44,51,56,78,88,150,153,156,169,184,188,203,208],"stochastic":[3],"multi-armed":[4],"bandit":[5],"(MAB)":[6],"problem":[7],"in":[8,28,64,112,126],"a":[9,12,16,73,83,119],"setting":[10],"where":[11,130],"player":[13],"can,":[14],"at":[15],"cost,":[17],"pre-observe":[18,181],"one":[19,25,139],"or":[20],"multiple":[21,134],"arms":[22,41,71,98,179],"before":[23,137],"playing":[24],"of":[26,178,187,210],"them":[27],"each":[29,65],"round.":[30],"Apart":[31],"from":[32],"classic":[34],"trade-off":[35],"between":[36,155],"exploration":[37],"(trying":[38],"out":[39],"more":[40,70],"to":[42,54,76,106,142,180],"find":[43],"best":[45,79],"one)":[46],"and":[47,165,200],"exploitation":[48],"(sticking":[49],"with":[50,99],"arm":[52,189],"believed":[53],"offer":[55],"highest":[57],"reward),":[58],"we":[59,148],"encounter":[60],"an":[61,93,175],"additional":[62],"dilemma":[63],"single":[66],"round,":[67],"i.e.,":[68],"pre-observing":[69],"gives":[72],"higher":[74],"chance":[75],"play":[77],"one,":[80],"but":[81],"incurs":[82],"larger":[84],"cost":[85,209],"which":[86,102,141,172],"decreases":[87],"overall":[89,158],"reward.":[90],"design":[92],"Observe-Before-Play":[94],"(OBP)":[95],"policy":[96,121,164,196],"for":[97,122],"Bernoulli":[100],"rewards,":[101],"could":[103,117],"be":[104],"generalized":[105],"any":[107],"i.i.d.":[108],"reward":[109,159],"distributions":[110],"bounded":[111],"[0,":[113],"1].":[114],"Our":[115],"strategy":[116],"enable":[118],"better":[120],"secondary":[123],"spectrum":[124],"access":[125],"Cognitive":[127],"Ratio":[128],"Networks,":[129],"users":[131],"can":[132,201],"sense":[133],"channels'":[135],"occupancies":[136],"choosing":[138],"on":[140,183],"transmit.":[143],"To":[144],"evaluate":[145],"our":[146,162,194],"policy,":[147],"define":[149],"regret":[151,199],"as":[152],"gap":[154],"expected":[157,170],"gained":[160],"by":[161,168],"OBP":[163,195],"that":[166,193],"obtained":[167],"optimum,":[171],"always":[173],"chooses":[174],"optimal":[176],"sequence":[177],"based":[182],"perfect":[185],"knowledge":[186],"distributions.":[190],"Experiments":[191],"show":[192],"has":[197],"sub-linear":[198],"outperform":[202],"classical":[204],"MAB":[205],"algorithm":[206],"when":[207],"pre-observations":[211],"is":[212],"relatively":[213],"low.":[214]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}