{"id":"W4400467706","doi":"10.1101/2024.07.08.602539","title":"Humans forage for reward in reinforcement learning tasks","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Jacobs Foundation; Frederick Gardner Cottrell Foundation; National Institutes of Health; Research Corporation for Science Advancement","keywords":"Reinforcement; Forage; Reinforcement learning; Psychology; Animal learning; Cognitive psychology; Computer science; Artificial intelligence; Social psychology; Biology; Agronomy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001030725,0.000464796,0.0004261717,0.0002280583,0.0003054293,0.00107994,0.0004192613,0.0007663168,0.002127675],"category_scores_gemma":[0.01038177,0.000268954,0.0003356631,0.0001971303,0.0005187755,0.001480352,0.0005101244,0.0007842197,0.0005412499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003232713,"about_ca_system_score_gemma":0.000303675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001165802,"about_ca_topic_score_gemma":0.001160695,"domain_scores_codex":[0.9995583,0.0001884137,0.00001932022,0.0001163522,0.00008737761,0.00003033614],"domain_scores_gemma":[0.9972001,0.001854655,0.0003070186,0.0003689656,0.0001182944,0.0001508892],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001805856,0.001019694,0.1474258,0.0005515364,0.0004289927,0.0008002859,0.002775765,0.264383,0.08744381,0.1043243,0.009442657,0.3795982],"study_design_scores_gemma":[0.00009006503,0.0003464426,0.03294059,0.00004300856,0.00004198191,0.0003671649,0.0002637711,0.7748168,0.009326031,0.1780041,0.003693369,0.00006669865],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8532044,0.0003744866,0.1341238,0.000707682,0.00003794804,0.0000553663,0.0001958833,0.0004906097,0.01080973],"genre_scores_gemma":[0.9753209,0.00008240106,0.02357899,0.00009224108,0.00001068728,0.00002726555,0.00009683049,0.0000434712,0.0007472539],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002127675,"threshold_uncertainty_score":0.007117808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07656178754497622,"score_gpt":0.3205034029806226,"score_spread":0.2439416154356464,"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."}}