{"id":"https://openalex.org/W2953337808","doi":"https://doi.org/10.1145/3292500.3330864","title":"Off-policy Learning for Multiple Loggers","display_name":"Off-policy Learning for Multiple Loggers","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2953337808","doi":"https://doi.org/10.1145/3292500.3330864","mag":"2953337808"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330864","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3330864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","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/A5100661188","display_name":"He Li","orcid":"https://orcid.org/0000-0002-2376-0665"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li He","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103251082","display_name":"Long Xia","orcid":"https://orcid.org/0000-0003-2580-6206"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Xia","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004548666","display_name":"Wei Zeng","orcid":"https://orcid.org/0000-0002-8343-6250"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zeng","raw_affiliation_strings":["Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078600050","display_name":"Zhi-Ming Ma","orcid":"https://orcid.org/0000-0001-6453-4368"},"institutions":[{"id":"https://openalex.org/I4210088861","display_name":"Chinese Academy of Science South America Center for Astronomy","ror":"https://ror.org/0051xhq65","country_code":"CL","type":"facility","lineage":["https://openalex.org/I4210088861"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Zhi-Ming Ma","raw_affiliation_strings":["Academy of Mathematics and Systems Science, CAS, Beijing, Chile"],"affiliations":[{"raw_affiliation_string":"Academy of Mathematics and Systems Science, CAS, Beijing, Chile","institution_ids":["https://openalex.org/I4210088861"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100816826","display_name":"Yihong Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihong Zhao","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054482111","display_name":"Dawei Yin","orcid":"https://orcid.org/0000-0002-8846-2001"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Yin","raw_affiliation_strings":["JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100661188"],"corresponding_institution_ids":["https://openalex.org/I4210103986"],"apc_list":null,"apc_paid":null,"fwci":0.5942,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71904197,"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":"1184","last_page":"1193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9977999925613403,"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":0.9977999925613403,"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/T12288","display_name":"Optimization and Search Problems","score":0.996999979019165,"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"}},{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.76752108335495},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6604588031768799},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6604049205780029},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.641974925994873},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6190237998962402},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.548714816570282},{"id":"https://openalex.org/keywords/empirical-risk-minimization","display_name":"Empirical risk minimization","score":0.5435677170753479},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48622575402259827},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.4671114683151245},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42053499817848206},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.23999446630477905},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10889145731925964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76752108335495},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6604588031768799},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6604049205780029},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.641974925994873},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6190237998962402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.548714816570282},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.5435677170753479},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48622575402259827},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.4671114683151245},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42053499817848206},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.23999446630477905},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10889145731925964},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3330864","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3330864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320336876","display_name":"National Center for Mathematics and Interdisciplinary Sciences, Chinese Academy of Sciences","ror":"https://ror.org/00s97k668"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1542523037","https://openalex.org/W1986050895","https://openalex.org/W2008740515","https://openalex.org/W2020160576","https://openalex.org/W2028125409","https://openalex.org/W2086206379","https://openalex.org/W2137983211","https://openalex.org/W2138909795","https://openalex.org/W2150291618","https://openalex.org/W2151568819","https://openalex.org/W2153635508","https://openalex.org/W2166944917","https://openalex.org/W2463677609","https://openalex.org/W2604520541","https://openalex.org/W2769473018","https://openalex.org/W2788295351","https://openalex.org/W2799544270","https://openalex.org/W2963842088","https://openalex.org/W2997591727","https://openalex.org/W3009804075","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3104349857","https://openalex.org/W3146803896","https://openalex.org/W4214717370","https://openalex.org/W4233471163","https://openalex.org/W4251767710","https://openalex.org/W4293404332"],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2066431708","https://openalex.org/W4384133558","https://openalex.org/W3025615835","https://openalex.org/W173210993","https://openalex.org/W2069885834","https://openalex.org/W2177289819","https://openalex.org/W2522078129","https://openalex.org/W4385538764"],"abstract_inverted_index":{"It":[0],"is":[1,34],"well":[2],"known":[3],"that":[4,200],"the":[5,104,131,144,152,157,173,178,187,192,201,208],"historical":[6,60,84,110],"logs":[7],"are":[8,53,75],"used":[9],"for":[10,143,177],"evaluating":[11],"and":[12,21],"learning":[13,28,40,56,86,102,175],"policies":[14,87],"in":[15,41,63,96],"interactive":[16],"systems,":[17],"e.g.":[18,71,114],"recommendation,":[19],"search,":[20],"online":[22,26],"advertising.":[23],"Since":[24],"direct":[25],"policy":[27],"usually":[29,65],"harms":[30],"user":[31],"experiences,":[32],"it":[33],"more":[35],"crucial":[36],"to":[37,129,165,186,190],"apply":[38],"off-policy":[39,101],"real-world":[42],"applications":[43],"instead.":[44],"Though":[45],"there":[46],"have":[47],"been":[48],"some":[49],"existing":[50],"works,":[51],"most":[52],"focusing":[54],"on":[55,196],"with":[57,124],"one":[58],"single":[59],"policy.":[61],"However,":[62],"practice,":[64],"a":[66,166],"number":[67],"of":[68,82,134],"parallel":[69],"experiments,":[70],"multiple":[72,89,109],"AB":[73],"tests,":[74],"performed":[76],"simultaneously.":[77],"To":[78],"make":[79],"full":[80],"use":[81],"such":[83,135],"data,":[85,123],"from":[88,108,121],"loggers":[90],"becomes":[91],"necessary.":[92],"Motivated":[93],"by":[94],"this,":[95],"this":[97],"paper,":[98],"we":[99,138,171,183],"investigate":[100],"when":[103],"training":[105],"data":[106],"coming":[107],"policies.":[111],"Specifically,":[112],"policies,":[113],"neural":[115],"networks,":[116],"can":[117,162,184],"be":[118,163],"learned":[119],"directly":[120],"multi-logger":[122],"counterfactual":[125],"estimators.":[126],"In":[127],"order":[128],"understand":[130],"generalization":[132,140,153],"ability":[133],"estimator":[136],"better,":[137],"conduct":[139],"error":[141,154],"analysis":[142],"empirical":[145],"risk":[146,159],"minimization":[147],"problem.":[148,169],"We":[149],"then":[150],"introduce":[151],"bound":[155],"as":[156],"new":[158,179],"function,":[160],"which":[161],"reduced":[164],"constrained":[167,180],"optimization":[168],"Finally,":[170],"give":[172],"corresponding":[174],"algorithm":[176],"problem,":[181],"where":[182],"appeal":[185],"minimax":[188],"problems":[189],"control":[191],"constraints.":[193],"Extensive":[194],"experiments":[195],"benchmark":[197],"datasets":[198],"demonstrate":[199],"proposed":[202],"methods":[203],"achieve":[204],"better":[205],"performances":[206],"than":[207],"state-of-the-arts.":[209]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}