{"id":"W3016846277","doi":"10.3390/jrfm13040078","title":"Contracts for Difference: A Reinforcement Learning Approach","year":2020,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Markov decision process; Computer science; Partially observable Markov decision process; Temporal difference learning; Latency (audio); Reinforcement; Artificial intelligence; Long short term memory; Machine learning; Markov process; Markov chain; Recurrent neural network; Markov model; Artificial neural network; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004436814,0.0001226214,0.0003876475,0.0001793312,0.0001952826,0.0001530497,0.0003573934,0.0000469785,0.00001594485],"category_scores_gemma":[0.01010922,0.00008490824,0.0001599971,0.0003305017,0.00004114067,0.0001205045,0.0001469456,0.0002641831,0.000002662204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002029289,"about_ca_system_score_gemma":0.00002910582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000228599,"about_ca_topic_score_gemma":4.099668e-7,"domain_scores_codex":[0.9978614,0.0001860762,0.0007713718,0.0002239901,0.000753827,0.0002033461],"domain_scores_gemma":[0.9976473,0.0009896468,0.0008440214,0.0001105475,0.0002416933,0.0001667308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005837041,0.00002817395,0.004678137,0.00002466885,0.00001934012,0.00001240885,0.001170367,0.004300605,0.00001609055,0.003474729,0.002487719,0.9832041],"study_design_scores_gemma":[0.00510616,0.002128341,0.220082,0.00009310662,0.0002851057,0.00003302267,0.002316008,0.05800284,0.0000602234,0.03606392,0.6754047,0.0004245151],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06498036,0.000247952,0.9309823,0.0002185845,0.0002729809,0.0002727942,0.000001849263,0.000008006328,0.00301517],"genre_scores_gemma":[0.9271533,0.0003042618,0.0714683,0.0002863675,0.0003507103,0.000008644845,4.710479e-7,0.000008108327,0.0004197813],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9827796,"threshold_uncertainty_score":0.998229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0785121096819567,"score_gpt":0.3382825093813589,"score_spread":0.2597703996994022,"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."}}