{"id":"https://openalex.org/W7155866248","doi":"https://doi.org/10.1145/3774904.3792181","title":"Off-Policy Learning with Limited Supply","display_name":"Off-Policy Learning with Limited Supply","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7155866248","doi":"https://doi.org/10.1145/3774904.3792181"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792181","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792181","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792181","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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":["Keio University, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0007-4790-5092","affiliations":[{"raw_affiliation_string":"Keio University, Tokyo, 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/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ren Kishimoto","raw_affiliation_strings":["Institute of Science Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0002-7443-5325","affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134685549","display_name":"Bushun Kawagishi","orcid":"https://orcid.org/0009-0005-6472-4969"},"institutions":[{"id":"https://openalex.org/I16656306","display_name":"Meiji University","ror":"https://ror.org/02rqvrp93","country_code":"JP","type":"education","lineage":["https://openalex.org/I16656306"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Bushun Kawagishi","raw_affiliation_strings":["Meiji University, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0005-6472-4969","affiliations":[{"raw_affiliation_string":"Meiji University, Tokyo, Japan","institution_ids":["https://openalex.org/I16656306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102762244","display_name":"Yusuke Narita","orcid":"https://orcid.org/0000-0003-0314-3384"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yusuke Narita","raw_affiliation_strings":["Yale University, New Haven, CT, USA"],"raw_orcid":"https://orcid.org/0000-0003-0314-3384","affiliations":[{"raw_affiliation_string":"Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101782556","display_name":"Yasuo Yamamoto","orcid":"https://orcid.org/0009-0003-9257-9063"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yasuo Yamamoto","raw_affiliation_strings":["LY Corporation, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0003-9257-9063","affiliations":[{"raw_affiliation_string":"LY Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017387514","display_name":"Nobuyuki Shimizu","orcid":"https://orcid.org/0000-0001-6767-3662"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobuyuki Shimizu","raw_affiliation_strings":["LY Corporation, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6767-3662","affiliations":[{"raw_affiliation_string":"LY Corporation, Tokyo, Japan","institution_ids":[]}]},{"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":["Cornell University, Ithaca, NY, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4357-5835","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, Japan","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45252525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5908","last_page":"5919"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9043999910354614,"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":0.9043999910354614,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.010900000110268593,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.010300000198185444,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5489000082015991},{"id":"https://openalex.org/keywords/supply-chain","display_name":"Supply chain","score":0.47760000824928284},{"id":"https://openalex.org/keywords/budget-constraint","display_name":"Budget constraint","score":0.42289999127388},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3991999924182892},{"id":"https://openalex.org/keywords/coupon","display_name":"Coupon","score":0.37130001187324524},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.3544999957084656},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.3393000066280365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7096999883651733},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5489000082015991},{"id":"https://openalex.org/C108713360","wikidata":"https://www.wikidata.org/wiki/Q1824206","display_name":"Supply chain","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3831999897956848},{"id":"https://openalex.org/C2779307704","wikidata":"https://www.wikidata.org/wiki/Q11794832","display_name":"Coupon","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3179999887943268},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2863999903202057},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792181","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792181","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792181","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792181","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.42606815695762634}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1094752974","https://openalex.org/W1998427280","https://openalex.org/W2014313807","https://openalex.org/W2767377948","https://openalex.org/W2784068709","https://openalex.org/W2790607499","https://openalex.org/W2997591727","https://openalex.org/W3003609932","https://openalex.org/W3197958031","https://openalex.org/W3200739262","https://openalex.org/W4213113302","https://openalex.org/W4292423901","https://openalex.org/W4382490899","https://openalex.org/W4388889271","https://openalex.org/W4391590817","https://openalex.org/W4396759029"],"related_works":[],"abstract_inverted_index":{"We":[0],"study":[1],"off-policy":[2],"learning":[3,171],"(OPL)":[4],"in":[5,13,29,46,115,121,156,226],"contextual":[6,30,227],"bandits,":[7],"which":[8],"plays":[9],"a":[10,14,37,108,131,166],"key":[11],"role":[12],"wide":[15],"range":[16],"of":[17,91,205],"real-world":[18,217],"applications":[19],"such":[20],"as":[21],"recommendation":[22],"systems":[23],"and":[24,53,147,216],"online":[25],"advertising.":[26],"Typical":[27],"OPL":[28,110,138,224],"bandits":[31],"assumes":[32],"an":[33],"unconstrained":[34,116],"environment":[35],"where":[36],"policy":[38,145],"can":[39],"select":[40],"the":[41,75,78,83,127,144,180,183,198],"same":[42],"item":[43,76,181],"infinitely.":[44],"However,":[45],"many":[47],"practical":[48],"applications,":[49],"including":[50],"coupon":[51],"allocation":[52,204],"e-commerce,":[54],"limited":[55,122,157,208,231],"supply":[56,123,158],"constrains":[57],"items":[58,190,206],"through":[59],"budget":[60],"limits":[61],"on":[62,68,161,189,213],"distributed":[63],"coupons":[64],"or":[65],"inventory":[66],"restrictions":[67],"products.":[69],"In":[70],"these":[71],"settings,":[72],"greedily":[73],"selecting":[74,179],"with":[77,151,172,182,191,207,230],"highest":[79,184],"expected":[80,105,185,194],"reward":[81],"for":[82,97],"current":[84],"user":[85],"may":[86,118,140],"lead":[87],"to":[88,142,197],"early":[89],"depletion":[90],"that":[92,112,135,149,220],"item,":[93],"making":[94],"it":[95],"unavailable":[96],"future":[98],"users":[99],"who":[100],"could":[101],"potentially":[102],"generate":[103],"higher":[104,193],"rewards.":[106],"As":[107],"result,":[109],"methods":[111,225],"are":[113],"optimal":[114],"settings":[117],"become":[119],"suboptimal":[120],"settings.":[124,159],"To":[125],"address":[126],"issue,":[128],"we":[129,164],"provide":[130],"theoretical":[132],"analysis":[133],"showing":[134],"conventional":[136],"greedy":[137],"approaches":[139],"fail":[141],"maximize":[143],"performance,":[146],"demonstrate":[148],"policies":[150],"superior":[152],"performance":[153],"must":[154],"exist":[155],"Based":[160],"this":[162],"insight,":[163],"introduce":[165],"novel":[167],"method":[168],"called":[169],"Off-Policy":[170],"Limited":[173],"Supply":[174],"(OPLS).":[175],"Rather":[176],"than":[177],"simply":[178],"reward,":[186],"OPLS":[187,221],"focuses":[188],"relatively":[192],"rewards":[195],"compared":[196],"other":[199],"users,":[200],"enabling":[201],"more":[202],"efficient":[203],"supply.":[209,232],"Our":[210],"empirical":[211],"results":[212],"both":[214],"synthetic":[215],"datasets":[218],"show":[219],"outperforms":[222],"existing":[223],"bandit":[228],"problems":[229]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-04-28T00:00:00"}