{"id":"W197688093","doi":"","title":"An Architecture for Distinguishing between Predictors and Inhibitors in Reinforcement Learning","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Reinforcement learning; Reinforcement; Outcome (game theory); Artificial intelligence; Valence (chemistry); Value (mathematics); Machine learning; Computer science; Predictive value; Stimulus (psychology); Psychology; Mathematics; Cognitive psychology; Social psychology; Physics","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":[0.001580438,0.0008175822,0.0007449864,0.0004501741,0.000493272,0.001495747,0.002074622,0.001541447,0.003321885],"category_scores_gemma":[0.003736883,0.0006435062,0.0006318246,0.0003139751,0.001209996,0.00250102,0.001346621,0.002553357,0.0008994524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001086685,"about_ca_system_score_gemma":0.001259346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003294454,"about_ca_topic_score_gemma":0.004101754,"domain_scores_codex":[0.9994831,0.0001223721,0.00004470855,0.000171697,0.0001031558,0.00007493867],"domain_scores_gemma":[0.99878,0.000528452,0.0001290648,0.0001948676,0.0002577254,0.0001099222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008198754,0.0005419934,0.007851701,0.0002813339,0.0002871441,0.0002740656,0.0004941205,0.420043,0.02734173,0.1074141,0.004723759,0.4299273],"study_design_scores_gemma":[0.00003379817,0.0001034456,0.000383036,0.00001725284,0.00004559253,0.00005027697,0.0000128817,0.9579807,0.003849377,0.03640971,0.001093672,0.00002015384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03125174,0.0002143342,0.9623787,0.0004895896,0.0001007455,0.00008087425,0.00007130556,0.002169115,0.00324346],"genre_scores_gemma":[0.7934608,0.0002177621,0.1999616,0.000336043,0.00007386914,0.0002538677,0.0001731457,0.00009156483,0.005431195],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003321885,"threshold_uncertainty_score":0.01111281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1580840457850106,"score_gpt":0.2435297391578026,"score_spread":0.08544569337279201,"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."}}