{"id":"W3012922890","doi":"10.1007/s10614-021-10119-4","title":"Reinforcement Learning in Economics and Finance","year":2021,"lang":"en","type":"preprint","venue":"Computational Economics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; AXA Research Fund","keywords":"Reinforcement learning; Action (physics); Computer science; Set (abstract data type); Artificial intelligence; Time horizon; Q-learning; Behavioral economics; Order (exchange); Reinforcement; Process (computing); Term (time); Temporal difference learning; Economics; Microeconomics; Psychology; Finance; Social psychology","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001303272,0.0002269804,0.000522993,0.0004265542,0.0001119368,0.0006644448,0.0005682223,0.0001849652,0.00006807801],"category_scores_gemma":[0.000709448,0.0002571457,0.0001009405,0.0001402117,0.0001367284,0.0003420113,0.001714342,0.000718164,0.00005490449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003990864,"about_ca_system_score_gemma":0.0008723559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002192565,"about_ca_topic_score_gemma":0.00009963075,"domain_scores_codex":[0.9974141,0.0001081483,0.001000888,0.0009634701,0.0002277635,0.0002856171],"domain_scores_gemma":[0.9974328,0.001394697,0.0004697371,0.0003828318,0.000249653,0.00007033753],"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":[0.00001043695,0.00001195515,0.0007932757,0.000005459221,0.00001225676,0.000006397229,0.0002224054,0.9329857,6.783598e-8,0.001967677,0.00003939457,0.06394499],"study_design_scores_gemma":[0.0003207507,0.00001733862,0.008307798,0.00002107315,0.000001677753,0.000007691515,0.0001936998,0.845167,0.000005699226,0.1377509,0.007994148,0.0002121401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8859991,0.0005210277,0.1104807,0.001048737,0.0006174266,0.0003189278,0.00002249926,0.00001932109,0.0009722052],"genre_scores_gemma":[0.9707885,0.004463106,0.02288628,0.0001855022,0.0001487226,0.00004487997,0.0002086166,0.00002803076,0.001246361],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1357832,"threshold_uncertainty_score":0.9999881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08548769842633776,"score_gpt":0.3792800501201351,"score_spread":0.2937923516937974,"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."}}