{"id":"W7126431021","doi":"10.21428/594757db.f235c2ea","title":"Deep Reinforcement Learning Algorithms for FinancialDecision-Making","year":2024,"lang":"en","type":"article","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Reinforcement learning; Benchmarking; Variety (cybernetics); Portfolio; Computational finance; Task (project management); Limiting","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01110644,0.0001906275,0.0003061511,0.0005236733,0.000342591,0.0007984177,0.0006710233,0.0001016132,0.001883236],"category_scores_gemma":[0.03826316,0.0001324713,0.0002888789,0.00124312,0.00004979291,0.0003396407,0.0002694516,0.0002304337,0.0004676447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000899328,"about_ca_system_score_gemma":0.0001246519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006525978,"about_ca_topic_score_gemma":0.000008344301,"domain_scores_codex":[0.9963952,0.0001971336,0.0008498362,0.0007531498,0.001362727,0.0004419582],"domain_scores_gemma":[0.9817955,0.01718854,0.0001304474,0.000463536,0.0003322834,0.00008962873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002740482,0.000004829883,0.00008253667,0.00000801655,0.00001135685,0.00001074123,0.0003286339,0.01590864,0.00004395825,0.009999159,0.01102138,0.9625533],"study_design_scores_gemma":[0.0001028852,0.0001045315,0.0002026825,0.00006148567,0.000009148964,0.00001369606,0.0002128398,0.6524263,0.0001368705,0.06877561,0.2778085,0.0001454446],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008611839,0.0003336979,0.9369335,0.0003688082,0.002191314,0.0003544441,6.958392e-7,0.000257496,0.05869885],"genre_scores_gemma":[0.4903661,0.000008429015,0.4586547,0.0002583477,0.000567683,0.0001011584,0.000002864648,0.00004399332,0.04999665],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9624079,"threshold_uncertainty_score":0.9990292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.145654509219241,"score_gpt":0.4503683971662779,"score_spread":0.3047138879470369,"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."}}