{"id":"W3113287941","doi":"10.2139/ssrn.4226484","title":"Estimating Policy Functions in Payments Systems Using Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Bank of Canada","funders":"","keywords":"Reinforcement learning; Payment; Reinforcement; Econometrics; Computer science; Economics; Actuarial science; Artificial intelligence; Finance; Psychology; Social psychology","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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.008559166,0.00009695073,0.0001530024,0.0005665072,0.001814391,0.0001724223,0.0004301599,0.00002323015,0.0002147355],"category_scores_gemma":[0.0005512066,0.00008671765,0.00008029826,0.001381346,0.00002938131,0.0002743981,0.0001485316,0.001780803,0.0000624774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002203859,"about_ca_system_score_gemma":0.001620503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002189809,"about_ca_topic_score_gemma":0.00003141345,"domain_scores_codex":[0.996663,0.0004923805,0.0006615213,0.0002294046,0.0008587033,0.001095018],"domain_scores_gemma":[0.9990087,0.0001817246,0.0004682335,0.0001988798,0.00008162443,0.00006080802],"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":[0.00001262417,0.00002321384,0.002074454,4.747017e-7,0.00001481106,8.294697e-7,0.000209464,0.8575718,0.0001691854,0.1341886,0.00003270696,0.0057019],"study_design_scores_gemma":[0.0006499478,0.0002353183,0.0001792896,0.00001218677,0.00001564923,0.001170726,0.0442733,0.5165855,0.000009242537,0.420267,0.01638943,0.0002124507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3803216,0.0003470198,0.6157896,0.0005656647,0.0005816325,0.0002007738,0.000001780312,0.00003300403,0.002158916],"genre_scores_gemma":[0.9900596,0.00001141589,0.0001218045,0.00005990065,0.0002968785,0.00003432901,0.000002315235,0.00001096025,0.009402811],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6156678,"threshold_uncertainty_score":0.9994851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05307467813418264,"score_gpt":0.3702131802859517,"score_spread":0.3171385021517691,"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."}}