{"id":"W4220814865","doi":"10.1080/14697688.2022.2049356","title":"The reinforcement learning Kelly strategy","year":2022,"lang":"en","type":"article","venue":"Quantitative Finance","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Portfolio; Reinforcement; Computer science; Artificial intelligence; Face (sociological concept); Mathematical optimization; Operations research; Economics; Mathematics; Psychology; Sociology; Finance; 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":["sts"],"consensus_categories":[],"category_scores_codex":[0.003985124,0.0001191152,0.0001724295,0.0001176462,0.002497941,0.0002150754,0.001197413,0.00001678313,0.0006325433],"category_scores_gemma":[0.003507318,0.00007863519,0.00008198753,0.001299853,0.0002712219,0.000286409,0.000509561,0.0006050184,0.000598735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001192287,"about_ca_system_score_gemma":0.0001691691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002355569,"about_ca_topic_score_gemma":0.00001572314,"domain_scores_codex":[0.9958069,0.0006266505,0.0004695245,0.000438063,0.002213825,0.0004450696],"domain_scores_gemma":[0.9952174,0.003634067,0.0002913964,0.0004651835,0.0003501035,0.00004182594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001031754,0.00001813544,0.000272206,8.124951e-7,0.000007377576,0.00002286728,0.0006839294,0.8557788,0.00008709048,0.08047283,0.006635244,0.05591754],"study_design_scores_gemma":[0.0002925821,0.0009298717,0.003841579,0.000003214977,0.000001362153,0.000005839127,0.006612137,0.1896764,0.0002224127,0.04541057,0.7528445,0.0001595496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2196964,0.008930347,0.7084072,0.005706525,0.002289072,0.00188689,0.00006581417,0.000219568,0.05279821],"genre_scores_gemma":[0.9292367,0.000161712,0.001135412,0.00006218964,0.00002974556,0.0001521998,0.000004310646,0.00001359697,0.06920411],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7462092,"threshold_uncertainty_score":0.9988007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1802992795779892,"score_gpt":0.4634093563427167,"score_spread":0.2831100767647275,"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."}}