{"id":"W4252297965","doi":"10.2139/ssrn.3901432","title":"A Reinforcement Learning Model of Procedural Rationality","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Research in Systems and Signal Processing","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Brock University","funders":"","keywords":"Rationality; Reinforcement learning; Reinforcement; Psychology; Computer science; Mathematical economics; Artificial intelligence; Cognitive psychology; Economics; Social psychology; Epistemology; Philosophy","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":[],"consensus_categories":[],"category_scores_codex":[0.0006813654,0.0000771478,0.0001261055,0.00003886288,0.0001158065,0.00002523847,0.00008041586,0.00003369492,0.00001591047],"category_scores_gemma":[0.00008431743,0.00007015753,0.00005832913,0.0001208421,0.00001770106,0.0001964574,0.00001704089,0.00108055,0.000002242379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003817115,"about_ca_system_score_gemma":0.001381379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001620773,"about_ca_topic_score_gemma":0.00001220455,"domain_scores_codex":[0.9984975,0.00002706544,0.0002664375,0.00007519116,0.0002849968,0.0008487554],"domain_scores_gemma":[0.9996276,0.00001780455,0.00005639415,0.00005707184,0.0001908287,0.00005028988],"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":[0.000007352812,0.000006127052,0.00006619348,0.00006221598,0.00005349148,0.000001507858,0.00009549264,0.9450071,0.0294705,0.02167972,0.00001518952,0.003535114],"study_design_scores_gemma":[0.0003561129,0.0000576972,0.000008476692,0.00007049547,0.000007754431,0.0001966102,0.0009530676,0.8979074,0.01055887,0.08948791,0.0002721423,0.0001233994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06963798,0.002958876,0.9236791,0.0000862118,0.00005040809,0.00005161656,4.384823e-7,0.00003888952,0.003496465],"genre_scores_gemma":[0.9965372,0.0009811473,0.0005239128,0.000009008159,0.00008466936,0.00000367689,0.000002848896,0.00001454403,0.001842994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9268992,"threshold_uncertainty_score":0.469451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01635224693011702,"score_gpt":0.2635554947981743,"score_spread":0.2472032478680572,"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."}}