{"id":"W3154082313","doi":"10.2139/ssrn.3743017","title":"Estimating Policy Functions in Payment Systems using Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Bank of Canada","funders":"","keywords":"Reinforcement learning; Payment; Reinforcement; Actuarial science; Computer science; Econometrics; Artificial intelligence; Business; Economics; 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":[0.007120959,0.001261553,0.002478307,0.001447438,0.0008075444,0.001845788,0.001714522,0.003088427,0.003043721],"category_scores_gemma":[0.03431325,0.001758194,0.000874025,0.0009375375,0.002212359,0.003115256,0.001922183,0.003904102,0.0004452017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002734881,"about_ca_system_score_gemma":0.002834509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01658327,"about_ca_topic_score_gemma":0.009884368,"domain_scores_codex":[0.9973775,0.001698885,0.0001229346,0.000346395,0.0002145807,0.0002396521],"domain_scores_gemma":[0.9442116,0.05182925,0.001405327,0.00066712,0.001232846,0.0006538612],"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":[0.00006989534,0.00004000606,0.000726338,0.00002532866,0.00002140659,0.00001789878,0.0000213855,0.9906036,0.00008521516,0.002628044,0.0001586477,0.005602199],"study_design_scores_gemma":[0.000008585852,0.000007957703,0.00004568171,0.000003145776,0.000002431517,0.000001587511,0.00000239965,0.9973828,0.00005071877,0.002473576,0.0000188239,0.000002227875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1130937,0.0003600671,0.8837628,0.0007709035,0.00006599537,0.0001281819,0.0001036605,0.0005212137,0.001193511],"genre_scores_gemma":[0.9425979,0.0001853818,0.05424561,0.0001252701,0.00004978494,0.0001787551,0.000160133,0.00007644112,0.002380848],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01658327,"threshold_uncertainty_score":0.03765965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01436104779690775,"score_gpt":0.2536797087303768,"score_spread":0.239318660933469,"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."}}