{"id":"W4311681269","doi":"10.22215/etd/2022-15153","title":"Deep Reinforcement Learning for Quantitative Finance: Time Series Forecasting using Proximal Policy Optimization","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Software portability; Reinforcement learning; Computer science; Artificial intelligence; Machine learning; Sequence (biology); Deep learning; Space (punctuation); Feature (linguistics); Series (stratigraphy)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001392584,0.0006498282,0.0008704176,0.000373793,0.0002450915,0.00105018,0.0007129024,0.00106401,0.002351313],"category_scores_gemma":[0.004113626,0.0003487848,0.0005167947,0.0005469353,0.0008574091,0.0009965735,0.001113386,0.001872441,0.0003670736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001094912,"about_ca_system_score_gemma":0.001405471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00524602,"about_ca_topic_score_gemma":0.00271013,"domain_scores_codex":[0.9997101,0.0001311454,0.00001315337,0.00005318775,0.00006036856,0.00003201673],"domain_scores_gemma":[0.9989292,0.0007833426,0.00006870824,0.00004164187,0.0001243343,0.00005275892],"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":[0.00003296191,0.000040197,0.0003315067,0.00008135287,0.0000400783,0.00002821103,0.00004559819,0.91841,0.0006503721,0.04258424,0.001665589,0.03609],"study_design_scores_gemma":[0.0000030508,0.000006171277,0.00003406905,0.000005914817,0.000002545569,0.000002526945,0.000001920075,0.991428,0.0001027093,0.008116576,0.0002944308,0.000002113816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009961642,0.001194473,0.9843578,0.0006788788,0.00007487598,0.00002330241,0.00003741781,0.0001953925,0.003476227],"genre_scores_gemma":[0.8048941,0.003247996,0.1799449,0.000295506,0.0002577189,0.000222999,0.0001836095,0.00013867,0.01081447],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00524602,"threshold_uncertainty_score":0.01043093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1328827027321908,"score_gpt":0.4344314375910162,"score_spread":0.3015487348588254,"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."}}