{"id":"https://openalex.org/W4406809903","doi":"https://doi.org/10.1145/3691326","title":"Estimating Policy Functions in Payment Systems Using Reinforcement Learning","display_name":"Estimating Policy Functions in Payment Systems Using Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-24","ids":{"openalex":"https://openalex.org/W4406809903","doi":"https://doi.org/10.1145/3691326"},"language":"en","primary_location":{"id":"doi:10.1145/3691326","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3691326","pdf_url":null,"source":{"id":"https://openalex.org/S4210173995","display_name":"ACM Transactions on Economics and Computation","issn_l":"2167-8375","issn":["2167-8375","2167-8383"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Economics and Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068291173","display_name":"Pablo Samuel Castro","orcid":"https://orcid.org/0000-0002-3206-336X"},"institutions":[{"id":"https://openalex.org/I4210148186","display_name":"Google (Canada)","ror":"https://ror.org/04d06q394","country_code":"CA","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969","https://openalex.org/I4210148186"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Pablo Castro","raw_affiliation_strings":["Brain Team, Google Research, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0002-3206-336X","affiliations":[{"raw_affiliation_string":"Brain Team, Google Research, Montreal, Canada","institution_ids":["https://openalex.org/I4210148186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016916553","display_name":"Ajit Desai","orcid":"https://orcid.org/0000-0001-7098-3186"},"institutions":[{"id":"https://openalex.org/I898769471","display_name":"Bank of Canada","ror":"https://ror.org/05cc98565","country_code":"CA","type":"other","lineage":["https://openalex.org/I898769471"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ajit Desai","raw_affiliation_strings":["Banking and Payments Research, Bank of Canada, Ottawa, Canada"],"raw_orcid":"https://orcid.org/0000-0001-7098-3186","affiliations":[{"raw_affiliation_string":"Banking and Payments Research, Bank of Canada, Ottawa, Canada","institution_ids":["https://openalex.org/I898769471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017444322","display_name":"Han Du","orcid":"https://orcid.org/0009-0005-0256-180X"},"institutions":[{"id":"https://openalex.org/I898769471","display_name":"Bank of Canada","ror":"https://ror.org/05cc98565","country_code":"CA","type":"other","lineage":["https://openalex.org/I898769471"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Han Du","raw_affiliation_strings":["Bank of Canada, Ottawa, Canada","Bank of Canada,  Ottawa, Canada"],"raw_orcid":"https://orcid.org/0009-0005-0256-180X","affiliations":[{"raw_affiliation_string":"Bank of Canada, Ottawa, Canada","institution_ids":["https://openalex.org/I898769471"]},{"raw_affiliation_string":"Bank of Canada,  Ottawa, Canada","institution_ids":["https://openalex.org/I898769471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066966565","display_name":"Rodney Garratt","orcid":"https://orcid.org/0000-0002-2667-2556"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rodney Garratt","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, United States","University of California, Santa Barbara,  Santa Barbara, United States"],"raw_orcid":"https://orcid.org/0000-0002-2667-2556","affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, United States","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"University of California, Santa Barbara,  Santa Barbara, United States","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088319815","display_name":"Francisco Rivadeneyra","orcid":"https://orcid.org/0000-0003-1423-0467"},"institutions":[{"id":"https://openalex.org/I898769471","display_name":"Bank of Canada","ror":"https://ror.org/05cc98565","country_code":"CA","type":"other","lineage":["https://openalex.org/I898769471"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Francisco Rivadeneyra","raw_affiliation_strings":["Bank of Canada, Ottawa, Canada","Bank of Canada,  Ottawa, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1423-0467","affiliations":[{"raw_affiliation_string":"Bank of Canada, Ottawa, Canada","institution_ids":["https://openalex.org/I898769471"]},{"raw_affiliation_string":"Bank of Canada,  Ottawa, Canada","institution_ids":["https://openalex.org/I898769471"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068291173"],"corresponding_institution_ids":["https://openalex.org/I4210148186"],"apc_list":null,"apc_paid":null,"fwci":14.5255,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.98355113,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"13","issue":"1","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9911999702453613,"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"}},"topics":[{"id":"https://openalex.org/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9911999702453613,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9853000044822693,"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/T11182","display_name":"Auction Theory and Applications","score":0.9811000227928162,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8201240301132202},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6881911754608154},{"id":"https://openalex.org/keywords/payment","display_name":"Payment","score":0.6820467710494995},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3933253884315491},{"id":"https://openalex.org/keywords/actuarial-science","display_name":"Actuarial science","score":0.3542262315750122},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.3212437033653259},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.2747785747051239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25350332260131836},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22601711750030518},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09967753291130066},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.06213456392288208}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8201240301132202},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6881911754608154},{"id":"https://openalex.org/C145097563","wikidata":"https://www.wikidata.org/wiki/Q1148747","display_name":"Payment","level":2,"score":0.6820467710494995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3933253884315491},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.3542262315750122},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3212437033653259},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2747785747051239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25350332260131836},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22601711750030518},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09967753291130066},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.06213456392288208}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3691326","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3691326","pdf_url":null,"source":{"id":"https://openalex.org/S4210173995","display_name":"ACM Transactions on Economics and Computation","issn_l":"2167-8375","issn":["2167-8375","2167-8383"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Economics and Computation","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1519731369","https://openalex.org/W2031452844","https://openalex.org/W2119717200","https://openalex.org/W2163569945","https://openalex.org/W2540823983","https://openalex.org/W2791227334","https://openalex.org/W2890426576","https://openalex.org/W2921123283","https://openalex.org/W2966306606","https://openalex.org/W3011754248","https://openalex.org/W3124976988","https://openalex.org/W3189491017","https://openalex.org/W4214717370","https://openalex.org/W4228997196","https://openalex.org/W4300980372","https://openalex.org/W4310510889","https://openalex.org/W4385768075","https://openalex.org/W4400989831"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"This":[0],"article":[1],"uses":[2],"reinforcement":[3],"learning":[4],"(RL)":[5],"to":[6,27,40,54,116,127,137,148],"approximate":[7],"the":[8,23,33,41,44,47,50,70,88,93,103,118,133,159],"policy":[9,30,90],"rules":[10],"of":[11,22,35,37,46,69,95,102,120,135,154,161],"banks":[12],"participating":[13],"in":[14,74,80,109,142,151],"a":[15,29,65,81],"high-value":[16],"payment":[17,162],"system":[18,42],"(HVPS).":[19],"The":[20],"objective":[21],"RL":[24,85,136],"agents":[25,86,114],"is":[26],"learn":[28,87,115],"function":[31],"for":[32],"choice":[34],"amount":[36],"liquidity":[38,139],"provided":[39],"at":[43,52],"beginning":[45],"day":[48],"and":[49,124,144,157],"rate":[51],"which":[53],"pay":[55],"intraday":[56],"payments.":[57],"Individual":[58],"choices":[59],"have":[60],"complex":[61,111],"strategic":[62],"effects":[63],"precluding":[64],"closed":[66],"form":[67],"solution":[68],"optimal":[71,89],"policy,":[72],"except":[73],"simple":[75],"cases.":[76],"We":[77,105],"show":[78,132],"that,":[79,108],"stylized":[82],"two-agent":[83],"setting,":[84],"that":[91],"minimizes":[92],"cost":[94,119],"processing":[96,121],"their":[97,122,152],"individual":[98],"payments\u2014without":[99],"complete":[100],"knowledge":[101],"environment.":[104],"further":[106],"demonstrate":[107],"more":[110],"settings,":[112],"both":[113],"reduce":[117],"payments":[123],"effectively":[125],"respond":[126],"liquidity-delay":[128],"tradeoff.":[129],"Our":[130],"results":[131],"potential":[134],"solve":[138],"management":[140],"problems":[141],"HVPS":[143],"provide":[145],"new":[146],"tools":[147],"assist":[149],"policymakers":[150],"mandates":[153],"ensuring":[155],"safety":[156],"improving":[158],"efficiency":[160],"systems.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
