{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001323732,0.0006308032,0.0008588678,0.0003720424,0.0003483637,0.0008944934,0.001560809,0.001262893,0.004800577],"category_scores_gemma":[0.004240085,0.0004097371,0.0005280056,0.000271368,0.001092582,0.001428102,0.001131243,0.00179124,0.0004312371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009396081,"about_ca_system_score_gemma":0.001264861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003718277,"about_ca_topic_score_gemma":0.003117829,"domain_scores_codex":[0.9995092,0.0001579386,0.00002516616,0.0001076639,0.0001270336,0.0000730053],"domain_scores_gemma":[0.998511,0.0008777896,0.0001695839,0.0001071785,0.0002006422,0.000133653],"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":[0.00007705561,0.00008896044,0.0009988426,0.00004716334,0.0000383262,0.0001283114,0.00007187861,0.9030212,0.001669094,0.05159201,0.001074886,0.04119233],"study_design_scores_gemma":[0.000005710699,0.00001172684,0.0000298041,0.00000249908,0.000002244046,0.000006767848,0.000002041604,0.992388,0.0001340532,0.007214627,0.0002000263,0.000002563507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02041264,0.0001511602,0.9750241,0.0004528476,0.00005343067,0.00004302268,0.00004595959,0.000329377,0.003487527],"genre_scores_gemma":[0.8598008,0.0001265819,0.134359,0.0001898774,0.00005605371,0.0001031467,0.00006320635,0.00007447237,0.005227001],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004800577,"threshold_uncertainty_score":0.01605958,"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."}}