{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001537493,0.0000857409,0.0001092086,0.0004207046,0.0003155342,0.00010383,0.0001726935,0.00006502849,6.213278e-7],"category_scores_gemma":[0.000008376914,0.00009990858,0.00002372279,0.0003461728,0.00002512878,0.0001427872,0.00002070188,0.0001581706,0.000002600821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000170497,"about_ca_system_score_gemma":0.0000772175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002851413,"about_ca_topic_score_gemma":0.00002522415,"domain_scores_codex":[0.9993212,0.00002472908,0.0002546847,0.0002445198,0.00002814833,0.0001266898],"domain_scores_gemma":[0.9995788,0.00007486995,0.00007282682,0.00022577,0.00002546134,0.00002227532],"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":[0.000001580406,0.00002584304,0.00005873152,0.000007042454,0.00001061593,1.256937e-7,0.00009953119,0.8400715,0.0000101196,0.0512717,0.000001203235,0.108442],"study_design_scores_gemma":[0.0002436853,0.00003138309,0.0003149684,0.00002407903,0.000005202776,0.000004214884,0.00009665543,0.9860379,0.00004648629,0.01279962,0.0003178352,0.0000779542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1349393,0.00003426417,0.863242,0.001183696,0.0001687408,0.0001702872,7.181342e-7,0.00007398565,0.0001869457],"genre_scores_gemma":[0.9686937,0.00003194561,0.0310362,0.000117007,0.00001116077,0.00005392974,0.00000247261,0.000003579603,0.00005004572],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8337543,"threshold_uncertainty_score":0.4074154,"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."}}