{"id":"W1507174820","doi":"10.1007/978-3-540-89722-4_13","title":"Policy Iteration for Learning an Exercise Policy for American Options","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Stochastic processes and financial applications","field":"Economics, Econometrics and Finance","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Machine learning; Computational finance; Finance; Economics","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":[0.005324489,0.001483846,0.002550152,0.00117196,0.001114978,0.001878391,0.001951181,0.004116789,0.009500501],"category_scores_gemma":[0.0190989,0.001277654,0.00151423,0.0008604361,0.002805827,0.002880695,0.003764659,0.004960678,0.0008816868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001831622,"about_ca_system_score_gemma":0.002778986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005377396,"about_ca_topic_score_gemma":0.00459266,"domain_scores_codex":[0.9984486,0.0008953282,0.00007687304,0.0002176714,0.0002146465,0.0001469143],"domain_scores_gemma":[0.9878458,0.01069807,0.0002170093,0.0003189364,0.0005134026,0.0004066724],"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":[0.0002608467,0.0001411521,0.0007976119,0.0001029334,0.00005471603,0.00009778002,0.0002243721,0.8151469,0.0004324576,0.1291848,0.001971726,0.05158461],"study_design_scores_gemma":[0.0000205177,0.00001949691,0.00002305552,0.00001241779,0.000004843602,0.000007767665,0.00001080411,0.9605698,0.0001212256,0.03897379,0.0002305056,0.000005752144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01814143,0.0002128948,0.9754641,0.0004718529,0.0000711847,0.0001114944,0.0000554165,0.0003185981,0.005152931],"genre_scores_gemma":[0.5481918,0.0004465589,0.4361137,0.000380248,0.0001886078,0.0009389471,0.000385173,0.0003767508,0.01297822],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009500501,"threshold_uncertainty_score":0.03178233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02863105843116803,"score_gpt":0.2704698405771932,"score_spread":0.2418387821460252,"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."}}