{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008459106,0.001397604,0.002965766,0.001673154,0.0007264913,0.002414736,0.001912534,0.003199871,0.002739163],"category_scores_gemma":[0.04329896,0.001789029,0.0009063788,0.00105435,0.002228346,0.003375674,0.001832271,0.003842396,0.000428023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002458165,"about_ca_system_score_gemma":0.002708956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01238615,"about_ca_topic_score_gemma":0.006662052,"domain_scores_codex":[0.9968609,0.002094718,0.0001506348,0.0004091049,0.0002326001,0.0002521015],"domain_scores_gemma":[0.9485868,0.04725346,0.001716939,0.0006541821,0.001151408,0.0006372737],"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":[0.00007754411,0.00005657559,0.0008614801,0.00003728419,0.00003321276,0.00002199603,0.00002450374,0.9873389,0.00009998044,0.004304044,0.0001927409,0.006951799],"study_design_scores_gemma":[0.00001200597,0.00001225352,0.00007689185,0.000005876017,0.000004241464,0.000003091516,0.000004042316,0.9944941,0.00005999462,0.005292877,0.00003060365,0.000003925748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08732798,0.0003622673,0.9098905,0.0006458556,0.00005718611,0.0001194472,0.0000964008,0.0003397054,0.001160693],"genre_scores_gemma":[0.9294539,0.0002727118,0.06711814,0.0001286055,0.00006543629,0.0001873974,0.0001844509,0.00007385269,0.00251537],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01238615,"threshold_uncertainty_score":0.04473656,"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."}}