{"id":"https://openalex.org/W4367046712","doi":"https://doi.org/10.1145/3543507.3583448","title":"Offline Policy Evaluation in Large Action Spaces via Outcome-Oriented Action Grouping","display_name":"Offline Policy Evaluation in Large Action Spaces via Outcome-Oriented Action Grouping","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4367046712","doi":"https://doi.org/10.1145/3543507.3583448"},"language":"en","primary_location":{"id":"doi:10.1145/3543507.3583448","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583448","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583448","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 2023","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/10.1145/3543507.3583448","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103134427","display_name":"Jie Peng","orcid":"https://orcid.org/0000-0003-4170-7339"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jie Peng","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0003-4170-7339","affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079383053","display_name":"Hao Zou","orcid":"https://orcid.org/0000-0002-6000-6936"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zou","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0002-6000-6936","affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004072676","display_name":"Jiashuo Liu","orcid":"https://orcid.org/0000-0002-9159-1752"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiashuo Liu","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0002-9159-1752","affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058413405","display_name":"Shaoming Li","orcid":"https://orcid.org/0000-0002-4915-9958"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaoming Li","raw_affiliation_strings":["Meituan, China"],"raw_orcid":"https://orcid.org/0000-0002-4915-9958","affiliations":[{"raw_affiliation_string":"Meituan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090548335","display_name":"Yibao Jiang","orcid":"https://orcid.org/0000-0001-8985-9812"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yibao Jiang","raw_affiliation_strings":["Meituan, China"],"raw_orcid":"https://orcid.org/0000-0001-8985-9812","affiliations":[{"raw_affiliation_string":"Meituan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062247330","display_name":"Jian Pei","orcid":"https://orcid.org/0000-0002-2200-8711"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Pei","raw_affiliation_strings":["Duke University, USA"],"raw_orcid":"https://orcid.org/0000-0002-2200-8711","affiliations":[{"raw_affiliation_string":"Duke University, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009228005","display_name":"Peng Cui","orcid":"https://orcid.org/0000-0003-2957-8511"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Cui","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0003-2957-8511","affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103134427"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.9759,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86965102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1220","last_page":"1230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.979200005531311,"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":0.9714999794960022,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6999384164810181},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.6709623336791992},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6410425901412964},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6321251392364502},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.610042929649353},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5101588368415833},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4932634234428406},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44137388467788696},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.43203625082969666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40936213731765747},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.36966079473495483},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3285002112388611},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2297579050064087},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21619102358818054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6999384164810181},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.6709623336791992},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6410425901412964},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6321251392364502},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.610042929649353},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5101588368415833},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4932634234428406},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44137388467788696},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.43203625082969666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40936213731765747},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.36966079473495483},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3285002112388611},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2297579050064087},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21619102358818054},{"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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543507.3583448","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583448","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583448","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 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3543507.3583448","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583448","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583448","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 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1895014292","display_name":null,"funder_award_id":"No. U1936219, 62141607","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4427191711","display_name":null,"funder_award_id":"62141607","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5050118973","display_name":null,"funder_award_id":"U1936219,62141607","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7972761409","display_name":null,"funder_award_id":"U1936219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367046712.pdf","grobid_xml":"https://content.openalex.org/works/W4367046712.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1094752974","https://openalex.org/W2002646960","https://openalex.org/W2047221353","https://openalex.org/W2122124659","https://openalex.org/W2138909795","https://openalex.org/W2150291618","https://openalex.org/W2604520541","https://openalex.org/W2784068709","https://openalex.org/W3099420497","https://openalex.org/W3106254775","https://openalex.org/W4233471163","https://openalex.org/W4285965606","https://openalex.org/W6678276431","https://openalex.org/W6785766461"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W2975817033","https://openalex.org/W4256502920","https://openalex.org/W4387967938"],"abstract_inverted_index":{"Offline":[0],"policy":[1,13],"evaluation":[2],"(OPE)":[3],"aims":[4],"to":[5,52,132],"accurately":[6],"estimate":[7],"the":[8,36,87,99,106,134,140,174],"performance":[9],"of":[10,27,38,41,136,176],"a":[11,24,64,117,128],"hypothetical":[12],"using":[14],"only":[15],"historical":[16],"data,":[17,43],"which":[18,126],"has":[19],"drawn":[20],"increasing":[21,76],"attention":[22],"in":[23,139],"wide":[25],"range":[26],"applications":[28],"including":[29],"recommender":[30],"systems":[31],"and":[32,143,169],"personalized":[33,56],"medicine.":[34],"With":[35],"presence":[37],"rising":[39],"granularity":[40],"consumer":[42],"many":[44],"industries":[45],"started":[46],"exploring":[47],"larger":[48],"action":[49,77,103,123,137,146],"candidate":[50],"spaces":[51],"support":[53],"more":[54,71,151],"precise":[55],"action.":[57],"While":[58],"inverse":[59],"propensity":[60],"score":[61],"(IPS)":[62],"is":[63],"standard":[65],"OPE":[66],"estimator,":[67],"it":[68],"suffers":[69],"from":[70],"severe":[72],"variance":[73,89],"issues":[74],"with":[75,121],"spaces.":[78],"To":[79],"address":[80],"this":[81],"issue,":[82],"we":[83,115],"theoretically":[84],"prove":[85],"that":[86],"estimation":[88,153],"can":[90,108],"be":[91],"reduced":[92],"by":[93,113,154],"merging":[94],"actions":[95],"into":[96],"groups":[97],"while":[98,158],"distinction":[100],"among":[101],"these":[102],"effects":[104,138],"on":[105,166],"outcome":[107],"induce":[109],"extra":[110],"bias.":[111,162],"Motivated":[112],"these,":[114],"propose":[116],"novel":[118],"IPS":[119],"estimator":[120],"outcome-oriented":[122],"Grouping":[124],"(GroupIPS),":[125],"leverages":[127],"Lipschitz":[129],"regularized":[130],"network":[131],"measure":[133],"distance":[135],"embedding":[141],"space":[142],"merges":[144],"nearest":[145],"neighbors.":[147],"This":[148],"strategy":[149],"enables":[150],"robust":[152],"achieving":[155],"smaller":[156],"variances":[157],"inducing":[159],"minor":[160],"additional":[161],"Empirically,":[163],"extensive":[164],"experiments":[165],"both":[167],"synthetic":[168],"real":[170],"world":[171],"datasets":[172],"demonstrate":[173],"effectiveness":[175],"our":[177],"proposed":[178],"method.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}