{"id":"W3123503485","doi":"10.2139/ssrn.3514586","title":"Deep Hedging of Derivatives Using Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Stochastic processes and financial applications","field":"Economics, Econometrics and Finance","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement; Reinforcement learning; Artificial intelligence; Computer science; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000589464,0.00008458964,0.0002194059,0.0001315686,0.0001243032,0.00002075278,0.0001624973,0.00004065884,0.00004248587],"category_scores_gemma":[0.00006515518,0.00009449287,0.00007783247,0.000211227,0.00002272901,0.0001486296,0.00003328744,0.0005476135,0.00007272027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003083049,"about_ca_system_score_gemma":0.0002173028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006605785,"about_ca_topic_score_gemma":0.00001103127,"domain_scores_codex":[0.9986354,0.000002910128,0.0004200853,0.0001474857,0.0000365198,0.0007576212],"domain_scores_gemma":[0.9993235,0.00002204395,0.0004804905,0.000102447,0.00004433667,0.00002722206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008098769,0.00001333701,0.007785428,0.00000950271,0.00003940079,8.041243e-8,0.0001910754,0.008868261,0.0002378001,0.9814276,2.047474e-7,0.001419261],"study_design_scores_gemma":[0.0003890742,0.0001658756,0.0009316297,0.00002080592,0.000006406807,0.00003301564,0.0009171356,0.03889231,0.00009196124,0.9576223,0.0007786493,0.0001508253],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1474315,0.003050836,0.8470383,0.00005128446,0.00007760725,0.00008318319,5.200951e-7,0.000007716933,0.002259016],"genre_scores_gemma":[0.9982509,0.000416756,0.0009461374,0.00002814619,0.00007628778,0.000003216646,0.000001288657,0.00001396278,0.0002632766],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8508195,"threshold_uncertainty_score":0.3853307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01518483810390456,"score_gpt":0.2252696031373393,"score_spread":0.2100847650334348,"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."}}