{"id":"W4401971650","doi":"10.1016/j.nlm.2024.107974","title":"A bio-inspired reinforcement learning model that accounts for fast adaptation after punishment","year":2024,"lang":"en","type":"article","venue":"Neurobiology of Learning and Memory","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge; Mount Royal University","funders":"","keywords":"Reinforcement learning; Punishment (psychology); Adaptation (eye); Reinforcement; Artificial intelligence; Learning rule; Action (physics); Computer science; Psychology; Machine learning; Cognitive psychology; Artificial neural network; Cognitive science; Neuroscience; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004795923,0.0002144376,0.000252961,0.0002281164,0.0001771517,0.0001207769,0.0002683708,0.0001334636,0.00001044093],"category_scores_gemma":[0.00009909277,0.0001990174,0.00009902904,0.0001474433,0.0001149188,0.0003223384,0.0002227331,0.0004264382,0.00001294063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003555101,"about_ca_system_score_gemma":0.00008938943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005749833,"about_ca_topic_score_gemma":9.073274e-7,"domain_scores_codex":[0.9985077,0.0001174501,0.0003303076,0.0005067187,0.0001761823,0.0003616897],"domain_scores_gemma":[0.9992189,0.0002574791,0.0001676758,0.0002077199,0.0000785169,0.00006968919],"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":[0.00004170947,0.000008484853,0.0006505722,0.0001584869,0.00003748512,0.000004156499,0.00213113,0.9802468,0.00229437,0.0008184466,0.00008779423,0.01352049],"study_design_scores_gemma":[0.0003789234,0.0005967992,0.0002694182,0.0001089021,0.00003040753,0.00001087619,0.0001971892,0.9906067,0.001483543,0.00006614609,0.006059631,0.0001914155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08286841,0.0003023807,0.9144928,0.0004337201,0.0005042536,0.0003242016,0.000001076246,0.0002854434,0.000787753],"genre_scores_gemma":[0.9854758,0.0002179417,0.008527992,0.0001517377,0.00004568472,0.00006868882,0.00002135675,0.00002422199,0.005466531],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9059648,"threshold_uncertainty_score":0.8115692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02508569619655849,"score_gpt":0.2593185852134721,"score_spread":0.2342328890169136,"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."}}