{"id":"https://openalex.org/W7163050219","doi":"https://doi.org/10.1145/3774935.3807904","title":"Uncertainty-Aware Reinforcement Learning for Conversion-Optimized Content Gating","display_name":"Uncertainty-Aware Reinforcement Learning for Conversion-Optimized Content Gating","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7163050219","doi":"https://doi.org/10.1145/3774935.3807904"},"language":null,"primary_location":{"id":"doi:10.1145/3774935.3807904","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774935.3807904","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774935.3807904","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045225787","display_name":"Han Jun Yoon","orcid":"https://orcid.org/0009-0006-0499-1245"},"institutions":[{"id":"https://openalex.org/I139347817","display_name":"United States Postal Service","ror":"https://ror.org/008g9p546","country_code":"US","type":"government","lineage":["https://openalex.org/I139347817"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Jun Yoon","raw_affiliation_strings":["The Washington Post, DC, DC, USA"],"raw_orcid":"https://orcid.org/0009-0006-0499-1245","affiliations":[{"raw_affiliation_string":"The Washington Post, DC, DC, USA","institution_ids":["https://openalex.org/I139347817"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137535090","display_name":"Janith Weerasinghe","orcid":"https://orcid.org/0009-0003-1562-4211"},"institutions":[{"id":"https://openalex.org/I139347817","display_name":"United States Postal Service","ror":"https://ror.org/008g9p546","country_code":"US","type":"government","lineage":["https://openalex.org/I139347817"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Janith Weerasinghe","raw_affiliation_strings":["The Washington Post, DC, DC, USA"],"raw_orcid":"https://orcid.org/0009-0003-1562-4211","affiliations":[{"raw_affiliation_string":"The Washington Post, DC, DC, USA","institution_ids":["https://openalex.org/I139347817"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137554528","display_name":"Himanshu Jahagirdar","orcid":"https://orcid.org/0009-0004-7822-3463"},"institutions":[{"id":"https://openalex.org/I139347817","display_name":"United States Postal Service","ror":"https://ror.org/008g9p546","country_code":"US","type":"government","lineage":["https://openalex.org/I139347817"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Himanshu Jahagirdar","raw_affiliation_strings":["The Washington Post, DC, DC, USA"],"raw_orcid":"https://orcid.org/0009-0004-7822-3463","affiliations":[{"raw_affiliation_string":"The Washington Post, DC, DC, USA","institution_ids":["https://openalex.org/I139347817"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137607960","display_name":"Meng Ling","orcid":"https://orcid.org/0000-0001-6597-5448"},"institutions":[{"id":"https://openalex.org/I139347817","display_name":"United States Postal Service","ror":"https://ror.org/008g9p546","country_code":"US","type":"government","lineage":["https://openalex.org/I139347817"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Ling","raw_affiliation_strings":["The Washington Post, DC, DC, USA"],"raw_orcid":"https://orcid.org/0000-0001-6597-5448","affiliations":[{"raw_affiliation_string":"The Washington Post, DC, DC, USA","institution_ids":["https://openalex.org/I139347817"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078148618","display_name":"Suja Thomas","orcid":null},"institutions":[{"id":"https://openalex.org/I139347817","display_name":"United States Postal Service","ror":"https://ror.org/008g9p546","country_code":"US","type":"government","lineage":["https://openalex.org/I139347817"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suja Thomas","raw_affiliation_strings":["The Washington Post, DC, DC, USA"],"raw_orcid":"https://orcid.org/0009-0007-1881-436X","affiliations":[{"raw_affiliation_string":"The Washington Post, DC, DC, USA","institution_ids":["https://openalex.org/I139347817"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022406414","display_name":"Anuradha Uduwage","orcid":null},"institutions":[{"id":"https://openalex.org/I139347817","display_name":"United States Postal Service","ror":"https://ror.org/008g9p546","country_code":"US","type":"government","lineage":["https://openalex.org/I139347817"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anuradha Uduwage","raw_affiliation_strings":["The Washington Post, DC, DC, USA"],"raw_orcid":"https://orcid.org/0009-0001-1308-3154","affiliations":[{"raw_affiliation_string":"The Washington Post, DC, DC, USA","institution_ids":["https://openalex.org/I139347817"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015758545","display_name":"Sam Han","orcid":null},"institutions":[{"id":"https://openalex.org/I139347817","display_name":"United States Postal Service","ror":"https://ror.org/008g9p546","country_code":"US","type":"government","lineage":["https://openalex.org/I139347817"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Han","raw_affiliation_strings":["The Washington Post, DC, DC, USA"],"raw_orcid":"https://orcid.org/0009-0000-2988-1284","affiliations":[{"raw_affiliation_string":"The Washington Post, DC, DC, USA","institution_ids":["https://openalex.org/I139347817"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139347817"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"599","last_page":"602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.5550000071525574,"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"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.5550000071525574,"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"}},{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.0689999982714653,"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"}},{"id":"https://openalex.org/T12238","display_name":"Green IT and Sustainability","score":0.048900000751018524,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7264999747276306},{"id":"https://openalex.org/keywords/gating","display_name":"Gating","score":0.5192999839782715},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4309999942779541},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.39959999918937683},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.3840000033378601},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3605000078678131}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7264999747276306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6924999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5751000046730042},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.5192999839782715},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.39959999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39890000224113464},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.26579999923706055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774935.3807904","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774935.3807904","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774935.3807904","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774935.3807904","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.49441075325012207}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2112420033","https://openalex.org/W2145339207","https://openalex.org/W2792399644","https://openalex.org/W2809177341","https://openalex.org/W3002803388","https://openalex.org/W4360584316"],"related_works":[],"abstract_inverted_index":{"Publishers":[0],"increasingly":[1],"rely":[2],"on":[3],"access":[4],"gates":[5,16],"to":[6,13,24,36,55,93,96,109,117],"drive":[7],"registrations":[8],"and":[9,33,67,77,111,119,127],"subscriptions.":[10],"Determining":[11],"when":[12],"present":[14],"these":[15],"is":[17,31,83],"a":[18,61,125],"sequential":[19],"decision":[20],"problem":[21],"well":[22],"suited":[23],"reinforcement":[25],"learning":[26],"(RL).":[27],"However,":[28],"online":[29],"exploration":[30,135],"costly":[32],"risky":[34],"due":[35],"delayed":[37],"conversion":[38],"signals.":[39],"We":[40],"introduce":[41],"Uncertainty-Aware":[42],"Advantage-Weighted":[43],"Actor\u2013Critic":[44],"(UA-AWAC),":[45],"an":[46],"offline":[47,121],"RL":[48,122],"method":[49],"that":[50,102],"learns":[51],"from":[52],"logged":[53],"traffic":[54],"produce":[56],"conversion-ready":[57],"policies.":[58],"UA-AWAC":[59,103],"optimizes":[60],"multi-objective":[62],"reward":[63],"incorporating":[64],"subscriptions,":[65],"registrations,":[66],"engagement,":[68],"while":[69],"mitigating":[70],"distribution":[71],"shift":[72],"through":[73],"epistemic":[74],"uncertainty":[75],"modeling":[76],"pessimistic":[78],"value":[79],"targets.":[80],"The":[81],"policy":[82],"trained":[84],"using":[85],"advantage-weighted":[86],"behavioral":[87],"cloning":[88],"with":[89],"Kullback\u2013Leibler":[90],"(KL)":[91],"regularization":[92],"remain":[94],"close":[95],"historical":[97],"gating":[98,133],"behavior.":[99],"Experiments":[100],"show":[101],"improves":[104],"subscription":[105],"rate":[106,113],"by":[107,114],"up":[108],"10%":[110],"registration":[112],"62%":[115],"compared":[116],"baseline":[118],"state-of-the-art":[120],"methods,":[123],"demonstrating":[124],"practical":[126],"stable":[128],"solution":[129],"for":[130],"intelligent":[131],"content":[132],"where":[134],"risks":[136],"are":[137],"high.":[138]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-02T00:00:00"}