{"id":"W4411024748","doi":"10.1038/s41586-025-08929-9","title":"Multi-timescale reinforcement learning in the brain","year":2025,"lang":"en","type":"article","venue":"Nature","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"National Institute of Neurological Disorders and Stroke; National Institute on Deafness and Other Communication Disorders; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Reinforcement; Reinforcement learning; Neuroscience; Computer science; Cognitive science; Psychology; Artificial intelligence; Social psychology","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":[0.0003395077,0.0001694306,0.0002831454,0.0001881471,0.0002112886,0.0007306092,0.0004388847,0.0004597626,0.001376939],"category_scores_gemma":[0.00156919,0.0001579023,0.0001803512,0.0001405372,0.0006361966,0.001218887,0.0004903474,0.0006478016,0.000215529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004526273,"about_ca_system_score_gemma":0.0003083381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007102949,"about_ca_topic_score_gemma":0.000610643,"domain_scores_codex":[0.9999138,0.00002201344,0.000003631807,0.00002770967,0.00002045846,0.00001232413],"domain_scores_gemma":[0.9996662,0.0001362613,0.0000595361,0.00003847152,0.00003863602,0.00006091518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003408316,0.0002385798,0.01000503,0.0002516205,0.0002398091,0.0004251678,0.0003025764,0.3041786,0.214282,0.2415599,0.004458608,0.2237172],"study_design_scores_gemma":[0.00002949759,0.0001115461,0.01988714,0.00002309169,0.00002489648,0.000290422,0.00007258375,0.58282,0.006696807,0.3868117,0.003188535,0.00004384879],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6204664,0.005351912,0.3498974,0.003049623,0.0005250953,0.00002709167,0.0001571012,0.0005691018,0.01995636],"genre_scores_gemma":[0.9874288,0.0005652296,0.01070655,0.0000653242,0.000051733,0.000009661323,0.00002070612,0.00003267486,0.001119488],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001376939,"threshold_uncertainty_score":0.004606307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01282019341979938,"score_gpt":0.2788490326420329,"score_spread":0.2660288392222335,"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."}}