{"id":"W3184471030","doi":"","title":"Deep Reinforcement Learning for Optimal Stopping with Application in Financial Engineering","year":2021,"lang":"en","type":"article","venue":"Les Cahiers du GERAD","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal","funders":"","keywords":"Optimal stopping; Reinforcement learning; Computer science; Benchmark (surveying); Categorical variable; Stochastic control; Deep learning; Artificial intelligence; Mathematical optimization; Machine learning; Optimal control; Mathematics","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":[0.0008045597,0.000119409,0.0002040242,0.0002278974,0.0002141506,0.0001190111,0.0002528364,0.00008789581,0.00002772673],"category_scores_gemma":[0.002394523,0.0001041467,0.00005379063,0.0007791435,0.00006308989,0.0002501536,0.00006259281,0.0003518866,0.00001435444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002187847,"about_ca_system_score_gemma":0.0001115353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001054427,"about_ca_topic_score_gemma":0.00004071594,"domain_scores_codex":[0.9981596,0.0000445091,0.0003313177,0.0004212025,0.0006860211,0.0003573575],"domain_scores_gemma":[0.9986522,0.0006591624,0.00009227757,0.0002513846,0.0002693671,0.00007558326],"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":[0.00005366272,0.00001184947,0.0009765424,0.000009283101,0.000005012501,0.00002527955,0.0008344891,0.946993,0.0006875841,0.002572851,0.00002697855,0.04780345],"study_design_scores_gemma":[0.0009243516,0.00009872451,0.003535191,0.00001932798,0.000003516945,0.00001753677,0.0009391548,0.9694554,0.002468414,0.001099095,0.02123687,0.0002024553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1036644,0.0001053348,0.8955191,0.0002632474,0.00005970676,0.0002622958,5.657045e-7,0.00002967736,0.00009571775],"genre_scores_gemma":[0.9065232,0.000020076,0.09184491,0.00006195622,0.0001663957,0.0002022907,0.00001942899,0.00002107513,0.001140666],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8036742,"threshold_uncertainty_score":0.4246979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02369073774361516,"score_gpt":0.3158420411063364,"score_spread":0.2921513033627213,"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."}}