{"id":"W4322099996","doi":"10.48550/arxiv.2302.11835","title":"Reinforcement Learning for Combining Search Methods in the Calibration of Economic ABMs","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Complex Systems and Time Series Analysis","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universität Bielefeld; Banca d'Italia; European Commission; Institute for Catastrophic Loss Reduction","keywords":"Reinforcement learning; Benchmark (surveying); Computer science; Calibration; Scheme (mathematics); Artificial intelligence; Machine learning; Random search; Algorithm; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00185223,0.0001547799,0.0005317668,0.0004536837,0.0001120647,0.00006127743,0.0004833094,0.0001410497,0.0001443509],"category_scores_gemma":[0.00005130182,0.0001760128,0.000304872,0.0003116468,0.0000482303,0.0001099705,0.000335564,0.0002988437,0.00003356765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002056932,"about_ca_system_score_gemma":0.00004724253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004543478,"about_ca_topic_score_gemma":0.0003397094,"domain_scores_codex":[0.9985691,0.0001081698,0.0005705656,0.0005137713,0.00001616675,0.0002221911],"domain_scores_gemma":[0.9986343,0.0003047987,0.0005372272,0.0004617734,0.00002937495,0.00003256298],"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":[0.00001598944,0.000009431112,0.00836979,0.00008272789,0.00009293625,0.000001838277,0.0004588733,0.6751122,0.000002094932,0.3157553,0.00005157034,0.0000471597],"study_design_scores_gemma":[0.0003489208,0.0000571855,0.001453639,0.00003483148,0.00002613488,2.247598e-7,0.001078198,0.9491749,0.00001371711,0.04627493,0.001358644,0.0001787121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1661142,0.0001678962,0.8274292,0.0001909141,0.0004177873,0.0007493407,0.00005562013,0.00004294382,0.004832136],"genre_scores_gemma":[0.9956078,0.0001426714,0.000554646,0.00001241693,0.00004807511,0.000006349821,0.00008699675,0.00002160067,0.00351947],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8294936,"threshold_uncertainty_score":0.7177594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2280180507669305,"score_gpt":0.2612564426857824,"score_spread":0.03323839191885189,"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."}}