{"id":"https://openalex.org/W4410089730","doi":"https://doi.org/10.1145/3696410.3714924","title":"Off-policy Evaluation for Multiple Actions in the Presence of Unobserved Confounders","display_name":"Off-policy Evaluation for Multiple Actions in the Presence of Unobserved Confounders","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4410089730","doi":"https://doi.org/10.1145/3696410.3714924"},"language":"en","primary_location":{"id":"doi:10.1145/3696410.3714924","doi":"https://doi.org/10.1145/3696410.3714924","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714924","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714924","source":{"id":"https://openalex.org/S7407088480","display_name":"International World Wide Web Conference (WWW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714924","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101749192","display_name":"Haolin Wang","orcid":"https://orcid.org/0000-0002-0477-4973","observed_orcids":["https://orcid.org/0000-0002-0477-4973"]},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107","https://openalex.org/I4405259444"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Haolin Wang","raw_affiliation_strings":["University of South Australia, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0477-4973","affiliations":[{"raw_affiliation_string":"University of South Australia, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383342","display_name":"Lin Liu","orcid":"https://orcid.org/0000-0003-2843-5738","observed_orcids":["https://orcid.org/0000-0003-2843-5738"]},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107","https://openalex.org/I4405259444"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lin Liu","raw_affiliation_strings":["University of South Australia, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0003-2843-5738","affiliations":[{"raw_affiliation_string":"University of South Australia, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012177739","display_name":"Jiuyong Li","orcid":"https://orcid.org/0000-0002-9023-1878","observed_orcids":["https://orcid.org/0000-0002-9023-1878","https://orcid.org/0000-0003-2843-5738"]},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107","https://openalex.org/I4405259444"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiuyong Li","raw_affiliation_strings":["University of South Australia, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9023-1878","affiliations":[{"raw_affiliation_string":"University of South Australia, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100743349","display_name":"Ziqi Xu","orcid":"https://orcid.org/0000-0003-1748-5801","observed_orcids":["https://orcid.org/0000-0003-1748-5801","https://orcid.org/0000-0001-9327-1026"]},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ziqi Xu","raw_affiliation_strings":["RMIT University, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1748-5801","affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029442609","display_name":"Jixue Liu","orcid":"https://orcid.org/0000-0002-0794-0404","observed_orcids":["https://orcid.org/0000-0002-0794-0404"]},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107","https://openalex.org/I4405259444"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jixue Liu","raw_affiliation_strings":["University of South Australia, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0794-0404","affiliations":[{"raw_affiliation_string":"University of South Australia, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007077356","display_name":"Zehong Cao","orcid":"https://orcid.org/0000-0003-3656-0328","observed_orcids":["https://orcid.org/0000-0003-3656-0328"]},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107","https://openalex.org/I4405259444"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zehong Cao","raw_affiliation_strings":["University of South Australia, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3656-0328","affiliations":[{"raw_affiliation_string":"University of South Australia, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065281913","display_name":"Debo Cheng","orcid":"https://orcid.org/0000-0002-0383-1462","observed_orcids":["https://orcid.org/0000-0002-0383-1462"]},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107","https://openalex.org/I4405259444"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Debo Cheng","raw_affiliation_strings":["University of South Australia, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0383-1462","affiliations":[{"raw_affiliation_string":"University of South Australia, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I170239107"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06364086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"413","last_page":"424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.004100000020116568,"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/T10845","display_name":"Advanced Causal Inference Techniques","score":0.002899999963119626,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/off-policy-evaluation","display_name":"off-policy evaluation","score":1.0},{"id":"https://openalex.org/keywords/unmeasured-confounding","display_name":"unmeasured confounding","score":0.8980000019073486},{"id":"https://openalex.org/keywords/auxiliary-variables","display_name":"auxiliary variables","score":0.8539999723434448},{"id":"https://openalex.org/keywords/bias-mitigation","display_name":"bias mitigation","score":0.6230000257492065},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.47999998927116394},{"id":"https://openalex.org/keywords/observational-bias","display_name":"observational bias","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C77350462","wikidata":"https://www.wikidata.org/wiki/Q1125472","display_name":"Confounding","level":2,"score":0.8254755735397339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5451783537864685},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.45336678624153137},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.36306095123291016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1763746738433838}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3696410.3714924","doi":"https://doi.org/10.1145/3696410.3714924","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714924","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714924","source":{"id":"https://openalex.org/S7407088480","display_name":"International World Wide Web Conference (WWW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:digital.library.adelaide.edu.au:11541.2/43338","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11541.2/43338","pdf_url":null,"source":{"id":"https://openalex.org/S4306401835","display_name":"Adelaide Research & Scholarship (AR&S) (University of Adelaide)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5681781","host_organization_name":"The University of Adelaide","host_organization_lineage":["https://openalex.org/I5681781"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1145/3696410.3714924","raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3696410.3714924","doi":"https://doi.org/10.1145/3696410.3714924","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714924","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714924","source":{"id":"https://openalex.org/S7407088480","display_name":"International World Wide Web Conference (WWW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G34411200","display_name":"Build competency aware and assuring machine learning systems","funder_award_id":"DP230101122","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G8327365677","display_name":"A closed-loop human\u2013agent learning framework to enhance decision making","funder_award_id":"DE220100265","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410089730.pdf","grobid_xml":"https://content.openalex.org/works/W4410089730.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1516659296","https://openalex.org/W1687073395","https://openalex.org/W1965237197","https://openalex.org/W2045697015","https://openalex.org/W2121756366","https://openalex.org/W2165612525","https://openalex.org/W2273088453","https://openalex.org/W2416041116","https://openalex.org/W2560674852","https://openalex.org/W2740020751","https://openalex.org/W2751985878","https://openalex.org/W2788575380","https://openalex.org/W2897367976","https://openalex.org/W2902572901","https://openalex.org/W2962685611","https://openalex.org/W2979842248","https://openalex.org/W2983831776","https://openalex.org/W2997841121","https://openalex.org/W3041564249","https://openalex.org/W3042897771","https://openalex.org/W3045025559","https://openalex.org/W3081008408","https://openalex.org/W3103956092","https://openalex.org/W3138456065","https://openalex.org/W4200424214","https://openalex.org/W4247950230","https://openalex.org/W4292232969","https://openalex.org/W4299828299","https://openalex.org/W4310895557","https://openalex.org/W4360584316","https://openalex.org/W4380989287","https://openalex.org/W4382318232","https://openalex.org/W4393159512","https://openalex.org/W6633423816"],"related_works":["https://openalex.org/W3045923282","https://openalex.org/W3104638933","https://openalex.org/W7093775209","https://openalex.org/W4313447125","https://openalex.org/W3172826213","https://openalex.org/W7103235586","https://openalex.org/W3212427392","https://openalex.org/W4376653493","https://openalex.org/W4221156642","https://openalex.org/W4221156641"],"abstract_inverted_index":{"Off-policy":[0],"evaluation":[1],"(OPE)":[2],"is":[3,14],"a":[4,22,30,104,133],"crucial":[5],"problem":[6],"in":[7,73,83,88,111,184,188],"reinforcement":[8],"learning":[9],"(RL),":[10],"where":[11,91],"the":[12,17,50,120,138,146,161],"goal":[13],"to":[15,59,175],"estimate":[16],"long-term":[18],"cumulative":[19],"reward":[20],"of":[21,122,160],"target":[23,162],"policy":[24,163],"using":[25],"historical":[26],"data":[27],"generated":[28],"by":[29,130],"potentially":[31],"different":[32],"behaviour":[33],"policy.":[34],"In":[35,99],"many":[36,142],"real-world":[37],"applications,":[38,90],"such":[39],"as":[40,141,145],"precision":[41],"medicine":[42],"and":[43,53,182],"recommendation":[44],"systems,":[45],"unobserved":[46,71,115,186],"confounders":[47,72,187],"may":[48],"influence":[49],"action,":[51],"reward,":[52],"state":[54],"transition":[55],"dynamics,":[56],"which":[57],"leads":[58],"biased":[60],"estimates":[61],"if":[62],"not":[63],"properly":[64],"addressed.":[65],"While":[66],"existing":[67,176],"methods":[68,126],"for":[69,109,127,140],"handling":[70],"OPE":[74,110,190],"focus":[75],"on":[76],"single-action":[77],"settings,":[78],"they":[79],"are":[80],"less":[81],"effective":[82],"multi-action":[84,112,128,189],"scenarios":[85,129],"commonly":[86],"found":[87],"practical":[89],"an":[92,157],"agent":[93],"can":[94],"take":[95],"multiple":[96],"actions":[97],"simultaneously.":[98],"this":[100],"paper,":[101],"we":[102,151],"propose":[103],"novel":[105],"auxiliary":[106,124,135,143],"variable-aided":[107],"method":[108,155],"settings":[113],"with":[114],"confounders.":[116],"Our":[117],"approach":[118],"overcomes":[119],"limitations":[121],"traditional":[123],"variable":[125],"requiring":[131],"only":[132],"single":[134],"variable,":[136],"relaxing":[137],"need":[139],"variables":[144],"actions.":[147],"Through":[148],"theoretical":[149],"analysis,":[150],"prove":[152],"that":[153,168],"our":[154,169],"provides":[156],"unbiased":[158],"estimation":[159],"value.":[164],"Empirical":[165],"evaluations":[166],"demonstrate":[167],"estimator":[170],"achieves":[171],"better":[172],"performance":[173],"compared":[174],"baseline":[177],"methods,":[178],"highlighting":[179],"its":[180],"effectiveness":[181],"reliability":[183],"addressing":[185],"settings.":[191]},"counts_by_year":[],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2025-05-06T00:00:00"}
