{"id":"https://openalex.org/W4403222010","doi":"https://doi.org/10.1145/3640457.3688162","title":"\u0394-OPE: Off-Policy Estimation with Pairs of Policies","display_name":"\u0394-OPE: Off-Policy Estimation with Pairs of Policies","publication_year":2024,"publication_date":"2024-10-08","ids":{"openalex":"https://openalex.org/W4403222010","doi":"https://doi.org/10.1145/3640457.3688162"},"language":"en","primary_location":{"id":"doi:10.1145/3640457.3688162","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3688162","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688162","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/10.1145/3640457.3688162","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083237271","display_name":"Olivier Jeunen","orcid":"https://orcid.org/0000-0001-6256-5814"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Olivier Jeunen","raw_affiliation_strings":["ShareChat, United Kingdom"],"affiliations":[{"raw_affiliation_string":"ShareChat, United Kingdom","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090857651","display_name":"Aleksei Ustimenko","orcid":"https://orcid.org/0009-0006-4942-7779"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aleksei Ustimenko","raw_affiliation_strings":["ShareChat, United Kingdom"],"affiliations":[{"raw_affiliation_string":"ShareChat, United Kingdom","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083237271"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.548,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84682839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"878","last_page":"883"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980000257492065,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.7327322959899902},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.528538167476654},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.18674322962760925}],"concepts":[{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.7327322959899902},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.528538167476654},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.18674322962760925},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3640457.3688162","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3688162","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688162","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:10.1145/3640457.3688162","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3688162","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688162","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403222010.pdf","grobid_xml":"https://content.openalex.org/works/W4403222010.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1998427280","https://openalex.org/W2112420033","https://openalex.org/W2784068709","https://openalex.org/W2892888989","https://openalex.org/W2893318239","https://openalex.org/W2902572901","https://openalex.org/W2913491198","https://openalex.org/W2997352934","https://openalex.org/W3003609932","https://openalex.org/W3009804075","https://openalex.org/W3012881846","https://openalex.org/W3035404611","https://openalex.org/W3042645155","https://openalex.org/W3081226161","https://openalex.org/W3089214483","https://openalex.org/W3098679278","https://openalex.org/W3099420497","https://openalex.org/W3116249021","https://openalex.org/W3200328667","https://openalex.org/W3200739262","https://openalex.org/W3201286590","https://openalex.org/W4233471163","https://openalex.org/W4239207475","https://openalex.org/W4290931133","https://openalex.org/W4296604485","https://openalex.org/W4296604501","https://openalex.org/W4307302081","https://openalex.org/W4367860606","https://openalex.org/W4385688690","https://openalex.org/W4386977147","https://openalex.org/W4392384534","https://openalex.org/W4392384882","https://openalex.org/W4401857111","https://openalex.org/W4403220260"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"The":[0],"off-policy":[1,83],"paradigm":[2],"casts":[3],"recommendation":[4],"as":[5,26,28],"a":[6,81],"counterfactual":[7],"decision-making":[8],"task,":[9],"allowing":[10],"practitioners":[11],"to":[12,22,79],"unbiasedly":[13],"estimate":[14],"online":[15,34],"metrics":[16],"using":[17],"offline":[18],"data.":[19],"This":[20,76],"leads":[21],"effective":[23],"evaluation":[24],"metrics,":[25],"well":[27],"learning":[29],"procedures":[30],"that":[31,40,48,56],"directly":[32],"optimise":[33],"success.":[35],"Nevertheless,":[36],"the":[37,46,57],"high":[38],"variance":[39],"comes":[41],"with":[42,66],"unbiasedness":[43],"is":[44,55],"typically":[45],"crux":[47],"complicates":[49],"practical":[50],"applications.":[51],"An":[52],"important":[53],"insight":[54],"difference":[58],"between":[59],"policy":[60],"values":[61],"can":[62],"often":[63],"be":[64],"estimated":[65],"significantly":[67],"reduced":[68],"variance,":[69],"if":[70],"said":[71],"policies":[72],"have":[73],"positive":[74],"covariance.":[75],"allows":[77],"us":[78],"formulate":[80],"pairwise":[82],"estimation":[84],"task:":[85],"\u0394-OPE.":[86]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
