{"id":"W7104546539","doi":"10.2139/ssrn.5702723","title":"<p>Deep Reinforcement Learning for Optimal Trading with Partial Information</p>","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Probabilistic logic; Trading strategy; Pairs trade; Exploit; Volatility (finance); Embedding; Markov process; Artificial neural network","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":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow"],"category_scores_codex":[0.05718042,0.001717071,0.0023181,0.002615407,0.003710916,0.003184829,0.003894653,0.001037023,0.0008131926],"category_scores_gemma":[0.01412527,0.00145,0.001599608,0.002159748,0.0004624102,0.002723493,0.001333777,0.01219678,0.00009554494],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.006094376,"about_ca_system_score_gemma":0.02744919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002113146,"about_ca_topic_score_gemma":0.0001799079,"domain_scores_codex":[0.9758508,0.002101534,0.005657773,0.001776438,0.005130197,0.009483313],"domain_scores_gemma":[0.9833226,0.005746952,0.006002268,0.001456189,0.002706404,0.0007656433],"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":[0.003622361,0.00007905411,0.0002795171,0.0001322092,0.001336678,0.000006480161,0.002665761,0.5549607,0.00008107216,0.05421446,0.0005451377,0.3820766],"study_design_scores_gemma":[0.005404867,0.004000499,0.0001438539,0.001202919,0.0008733699,0.001347374,0.003806116,0.7654591,0.0002429041,0.06692196,0.1487398,0.00185726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01468925,0.002216855,0.9594441,0.001011021,0.003564351,0.002441662,0.00001512014,0.0001433736,0.01647423],"genre_scores_gemma":[0.8791717,0.005711721,0.08014058,0.0003153696,0.002750905,0.0006456655,0.0001268547,0.0001814517,0.03095575],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8793036,"threshold_uncertainty_score":0.9995576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03473964749428303,"score_gpt":0.3340389846265877,"score_spread":0.2992993371323047,"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."}}