{"id":"W4406809903","doi":"10.1145/3691326","title":"Estimating Policy Functions in Payment Systems Using Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Economics and Computation","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bank of Canada; Google (Canada)","funders":"","keywords":"Reinforcement learning; Reinforcement; Payment; Computer science; Actuarial science; Econometrics; Economics; Artificial intelligence; Psychology; Social psychology; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004073272,0.00130347,0.00179559,0.0007841472,0.000588468,0.001504754,0.001408589,0.00208403,0.001916131],"category_scores_gemma":[0.01859458,0.000881502,0.0005747974,0.0005861656,0.002090535,0.001837253,0.00126005,0.002589856,0.0003051534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002177416,"about_ca_system_score_gemma":0.002239386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01171924,"about_ca_topic_score_gemma":0.007754675,"domain_scores_codex":[0.9980958,0.001133117,0.0000797936,0.0002811546,0.0002008693,0.0002092466],"domain_scores_gemma":[0.9871088,0.01096921,0.0007840976,0.0002969271,0.0005686561,0.0002724135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003061605,0.00002521237,0.0005799156,0.00001750818,0.00001715519,0.00002062642,0.00001689723,0.9924496,0.00009533759,0.002949888,0.00011274,0.003684485],"study_design_scores_gemma":[0.000007928218,0.00000902493,0.00003722693,0.00000265857,0.000001932342,0.000002083617,0.000002770102,0.9968243,0.00005339901,0.003016574,0.0000398656,0.00000231429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08455902,0.0004935298,0.9114676,0.0007569952,0.00006546497,0.0001120639,0.00007568057,0.0004867861,0.001982741],"genre_scores_gemma":[0.9488281,0.0002121638,0.04890811,0.0001541072,0.00004023188,0.0001493761,0.00009141338,0.00003739496,0.001579126],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01171924,"threshold_uncertainty_score":0.02330202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01515121721046375,"score_gpt":0.2612452480946005,"score_spread":0.2460940308841367,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}