{"id":"https://openalex.org/W4403221787","doi":"https://doi.org/10.1145/3640457.3688099","title":"Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits","display_name":"Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits","publication_year":2024,"publication_date":"2024-10-08","ids":{"openalex":"https://openalex.org/W4403221787","doi":"https://doi.org/10.1145/3640457.3688099"},"language":"en","primary_location":{"id":"doi:10.1145/3640457.3688099","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3688099","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688099","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688099","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035138146","display_name":"Tatsuhiro Shimizu","orcid":"https://orcid.org/0009-0009-9746-3346"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tatsuhiro Shimizu","raw_affiliation_strings":["Independent Researcher, Japan"],"affiliations":[{"raw_affiliation_string":"Independent Researcher, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107599692","display_name":"K\u014dichi Tanaka","orcid":"https://orcid.org/0009-0007-4790-5092"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Tanaka","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Keio Univercity, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Keio Univercity, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093402702","display_name":"Ren Kishimoto","orcid":"https://orcid.org/0009-0002-7443-5325"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ren Kishimoto","raw_affiliation_strings":["Department of Industrial Engineering and Economics, Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Economics, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001514927","display_name":"Haruka Kiyohara","orcid":"https://orcid.org/0009-0000-6378-4365"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haruka Kiyohara","raw_affiliation_strings":["Computer Science, Cornell University, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science, Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101431510","display_name":"Masahiro Nomura","orcid":"https://orcid.org/0000-0002-4945-5984"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahiro Nomura","raw_affiliation_strings":["CyberAgent, Inc., Japan"],"affiliations":[{"raw_affiliation_string":"CyberAgent, Inc., Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101991694","display_name":"Yuta Saito","orcid":"https://orcid.org/0000-0003-4357-5835"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuta Saito","raw_affiliation_strings":["Computer Science, Cornell University, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science, Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5035138146"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4003,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.89550788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"733","last_page":"741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T11182","display_name":"Auction Theory and Applications","score":0.9947999715805054,"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":0.9835000038146973,"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":0.7300138473510742},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.546394944190979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5266756415367126},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5061284899711609},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44455912709236145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300138473510742},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.546394944190979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5266756415367126},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5061284899711609},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44455912709236145}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3640457.3688099","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3688099","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688099","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th ACM Conference on Recommender Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3640457.3688099","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3688099","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688099","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403221787.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1998427280","https://openalex.org/W2020160576","https://openalex.org/W2400213106","https://openalex.org/W2798460079","https://openalex.org/W3003609932","https://openalex.org/W3044963235","https://openalex.org/W3098679278","https://openalex.org/W3104589861","https://openalex.org/W3197958031","https://openalex.org/W3200739262","https://openalex.org/W3201265114","https://openalex.org/W3212929567","https://openalex.org/W4213113302","https://openalex.org/W4233471163","https://openalex.org/W4287118432","https://openalex.org/W4292423901","https://openalex.org/W4382203490","https://openalex.org/W4382490899","https://openalex.org/W4391590817","https://openalex.org/W4396723171","https://openalex.org/W4396757589","https://openalex.org/W4396759029","https://openalex.org/W6796524807"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"We":[0],"explore":[1],"off-policy":[2],"evaluation":[3],"and":[4,34,58,76,145,198,225],"learning":[5],"(OPE/L)":[6],"in":[7,18,52,66,102,210,222],"contextual":[8],"combinatorial":[9],"bandits":[10],"(CCB),":[11],"where":[12],"a":[13,16,27,35,114],"policy":[14],"selects":[15],"subset":[17,126],"the":[19,67,83,99,103,137,142,146,151,171,181],"action":[20,118],"space.":[21],"For":[22],"example,":[23],"it":[24],"might":[25],"choose":[26],"set":[28],"of":[29,62,105,116],"furniture":[30],"pieces":[31],"(a":[32],"bed":[33],"drawer)":[36],"from":[37,141,150],"available":[38,106],"items":[39],"(bed,":[40],"drawer,":[41],"chair,":[42],"etc.)":[43],"for":[44],"interior":[45],"design":[46],"sales.":[47],"This":[48,130],"setting":[49],"is":[50],"widespread":[51],"fields":[53],"such":[54,73],"as":[55,74,208],"recommender":[56],"systems":[57],"healthcare,":[59],"yet":[60],"OPE/L":[61,71],"CCB":[63,84],"remains":[64],"unexplored":[65],"relevant":[68],"literature.":[69],"Typical":[70],"methods":[72,197,204,221],"regression":[75,203],"importance":[77,165,195],"sampling":[78,196],"can":[79],"be":[80],"applied":[81],"to":[82,92,123,134,168,178,193,202],"problem,":[85],"however,":[86],"they":[87],"face":[88],"significant":[89],"challenges":[90],"due":[91],"high":[93],"bias":[94,199],"or":[95],"variance,":[96],"exacerbated":[97],"by":[98],"exponential":[100],"growth":[101],"number":[104],"subsets.":[107],"To":[108],"address":[109],"these":[110],"challenges,":[111],"we":[112],"introduce":[113],"concept":[115],"factored":[117],"space,":[119],"which":[120],"allows":[121,132],"us":[122,133],"decompose":[124],"each":[125],"into":[127],"binary":[128],"indicators.":[129],"formulation":[131],"distinguish":[135],"between":[136],"\u201cmain":[138],"effect\u201d":[139],"derived":[140],"main":[143,172],"actions,":[144,153],"\u201cresidual":[147],"effect\u201d,":[148],"originating":[149],"supplemental":[152],"facilitating":[154],"more":[155],"effective":[156],"OPE.":[157],"Specifically,":[158],"our":[159,211],"estimator,":[160],"called":[161],"OPCB,":[162],"leverages":[163],"an":[164],"sampling-based":[166],"approach":[167,177],"unbiasedly":[169],"estimate":[170],"effect,":[173],"while":[174],"employing":[175],"regression-based":[176],"deal":[179],"with":[180,184],"residual":[182],"effect":[183],"low":[185],"variance.":[186],"OPCB":[187],"achieves":[188],"substantial":[189],"variance":[190],"reduction":[191,200],"compared":[192],"conventional":[194],"relative":[201],"under":[205],"certain":[206],"conditions,":[207],"illustrated":[209],"theoretical":[212],"analysis.":[213],"Experiments":[214],"demonstrate":[215],"OPCB\u2019s":[216],"superior":[217],"performance":[218],"over":[219],"typical":[220],"both":[223],"OPE":[224],"OPL.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}