{"id":"https://openalex.org/W7163046226","doi":"https://doi.org/10.1145/3774935.3807911","title":"A Case Study of Offline Reinforcement Learning for Paywall Decisioning","display_name":"A Case Study of Offline Reinforcement Learning for Paywall Decisioning","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7163046226","doi":"https://doi.org/10.1145/3774935.3807911"},"language":null,"primary_location":{"id":"doi:10.1145/3774935.3807911","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774935.3807911","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/10.1145/3774935.3807911","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137608050","display_name":"Janith Weerasinghe","orcid":"https://orcid.org/0009-0003-1562-4211"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Janith Weerasinghe","raw_affiliation_strings":["The Washington Post, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0009-0003-1562-4211","affiliations":[{"raw_affiliation_string":"The Washington Post, Washington, DC, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045225787","display_name":"Han Jun Yoon","orcid":"https://orcid.org/0009-0006-0499-1245"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Jun Yoon","raw_affiliation_strings":["The Washington Post, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0009-0006-0499-1245","affiliations":[{"raw_affiliation_string":"The Washington Post, Washington, DC, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100937085","display_name":"Meng Ling","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Ling","raw_affiliation_strings":["The Washington Post, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0000-0001-6597-5448","affiliations":[{"raw_affiliation_string":"The Washington Post, Washington, DC, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137594865","display_name":"Himanshu Jahagirdar","orcid":"https://orcid.org/0009-0004-7822-3463"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Himanshu Jahagirdar","raw_affiliation_strings":["The Washington Post, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0009-0004-7822-3463","affiliations":[{"raw_affiliation_string":"The Washington Post, Washington, DC, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078148618","display_name":"Suja Thomas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suja Thomas","raw_affiliation_strings":["The Washington Post, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0009-0007-1881-436X","affiliations":[{"raw_affiliation_string":"The Washington Post, Washington, DC, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022406414","display_name":"Anuradha Uduwage","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anuradha Uduwage","raw_affiliation_strings":["The Washington Post, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0009-0001-1308-3154","affiliations":[{"raw_affiliation_string":"The Washington Post, Washington, DC, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137598135","display_name":"Sam Han","orcid":"https://orcid.org/0009-0000-2988-1284"},"institutions":[{"id":"https://openalex.org/I4210104650","display_name":"Graham Holdings (United States)","ror":"https://ror.org/01f93vk95","country_code":"US","type":"company","lineage":["https://openalex.org/I4210104650"]},{"id":"https://openalex.org/I4210138849","display_name":"Washington School of Psychiatry","ror":"https://ror.org/03zgbv316","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210138849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Han","raw_affiliation_strings":["The Washington Post, Washington, USA"],"raw_orcid":"https://orcid.org/0009-0000-2988-1284","affiliations":[{"raw_affiliation_string":"The Washington Post, Washington, USA","institution_ids":["https://openalex.org/I4210104650","https://openalex.org/I4210138849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"571","last_page":"574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.3278000056743622,"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"}},"topics":[{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.3278000056743622,"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"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.03099999949336052,"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/T13429","display_name":"Electricity Theft Detection Techniques","score":0.030899999663233757,"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":0.7904000282287598},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5512999892234802},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.526199996471405},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.49309998750686646},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.41690000891685486},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.3553999960422516}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7904000282287598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6919000148773193},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5512999892234802},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.526199996471405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49790000915527344},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3849000036716461},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C168563851","wikidata":"https://www.wikidata.org/wiki/Q1436668","display_name":"Randomized controlled trial","level":2,"score":0.27469998598098755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774935.3807911","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774935.3807911","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:10.1145/3774935.3807911","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774935.3807911","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":[{"score":0.676746666431427,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2273088453","https://openalex.org/W2809177341"],"related_works":[],"abstract_inverted_index":{"We":[0,20,58],"describe":[1],"how":[2],"The":[3,88],"Washington":[4],"Post":[5],"deployed":[6],"an":[7],"offline":[8,68,165],"reinforcement":[9],"learning":[10],"(RL)":[11],"system":[12,89],"to":[13,65,80,100,147,159],"optimize":[14],"paywall":[15],"decisioning":[16],"at":[17],"production":[18,56],"scale.":[19],"cast":[21],"each":[22],"non-subscriber":[23],"article":[24],"access":[25],"attempt":[26],"as":[27],"a":[28,49,61,66,96,104,122,130],"sequential":[29],"decision":[30],"with":[31,72,93],"three":[32],"actions:":[33],"free":[34],"access,":[35],"registration":[36,144],"wall,":[37],"or":[38],"subscription":[39],"paywall,":[40],"and":[41,54,82,95,120,141,163],"learn":[42],"policies":[43,113],"from":[44,60],"logged":[45],"data":[46],"collected":[47],"via":[48],"small-traffic":[50],"randomized":[51,98,135],"controlled":[52],"trial":[53],"subsequent":[55],"logging.":[57],"iterated":[59],"tabular":[62],"Q-learning":[63],"baseline":[64,136],"deep":[67],"RL":[69,149,166],"model":[70],"trained":[71],"Conservative":[73],"Q-Learning":[74],"(CQL),":[75],"using":[76],"off-policy":[77],"evaluation":[78],"primarily":[79],"screen":[81],"rank":[83],"candidates":[84],"before":[85],"online":[86,109],"testing.":[87],"was":[90],"rolled":[91],"out":[92],"guardrails":[94],"persistent":[97],"holdout":[99],"manage":[101],"risk":[102],"in":[103],"revenue-critical":[105],"setting.":[106],"In":[107],"year-long":[108],"experiments,":[110],"the":[111,115,126,134,143,155],"learned":[112],"outperformed":[114],"legacy":[116],"rules-based":[117],"metering":[118],"policy":[119,128],"improved":[121],"stakeholder-weighted":[123],"value":[124],"metric;":[125],"CQL":[127],"delivered":[129],"+3%":[131],"lift":[132],"versus":[133],"while":[137],"increasing":[138],"subscriptions":[139],"(+6%)":[140],"reducing":[142],"gap":[145],"relative":[146],"earlier":[148],"iterations.":[150],"This":[151],"case":[152],"study":[153],"highlights":[154],"practical":[156],"steps":[157],"needed":[158],"safely":[160],"train,":[161],"evaluate,":[162],"deploy":[164],"for":[167],"high-stakes":[168],"personalization.":[169]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-02T00:00:00"}