{"id":"W2904489222","doi":"10.48550/arxiv.1812.06600","title":"Double Deep Q-Learning for Optimal Execution","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Benchmark (surveying); Computer science; Limit (mathematics); Function (biology); Bellman equation; Artificial neural network; Value (mathematics); Control (management); Action (physics); State (computer science); Q-learning; Optimal control; Mathematical optimization; Artificial intelligence; Machine learning; Algorithm; Reinforcement learning; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005658734,0.0003927983,0.0005904927,0.000675203,0.0005105023,0.0003140094,0.002008102,0.0005358305,0.0005754977],"category_scores_gemma":[0.003948899,0.0004020678,0.0005332067,0.0009934719,0.0002910432,0.0003043014,0.001898141,0.0007042703,0.0003126873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002751461,"about_ca_system_score_gemma":0.000190833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006685861,"about_ca_topic_score_gemma":0.0000332169,"domain_scores_codex":[0.9960915,0.0006135231,0.0005161467,0.001847185,0.0003700893,0.0005615691],"domain_scores_gemma":[0.9939974,0.002580358,0.0008188126,0.001293755,0.001074337,0.0002353401],"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":[0.002316105,0.0001176371,0.01439917,0.00007394919,0.0001885749,0.0000804424,0.0007687103,0.9302593,0.0000785377,0.02051407,0.006140508,0.02506294],"study_design_scores_gemma":[0.001458773,0.0002268142,0.002770251,0.00007873889,0.0001623237,0.000008383147,0.0005301816,0.8512921,0.0002901476,0.1210488,0.02145928,0.0006742098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3795171,0.00002714003,0.6069074,0.00002870228,0.001279146,0.0004699469,0.000008661807,0.0001501918,0.01161174],"genre_scores_gemma":[0.9529352,0.0000186307,0.02838276,0.00003043176,0.0004203467,0.000005033457,0.00002495185,0.00004353237,0.01813915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5785246,"threshold_uncertainty_score":0.9998431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2709709277858849,"score_gpt":0.3182128170699396,"score_spread":0.04724188928405476,"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."}}