{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003919456,0.0004950706,0.0006453979,0.0003146581,0.0003410095,0.0006556304,0.001320295,0.001336774,0.002750435],"category_scores_gemma":[0.001025975,0.0002275431,0.0006076244,0.000230972,0.0007606003,0.0008929265,0.0004507105,0.001232171,0.0005686098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007191254,"about_ca_system_score_gemma":0.000721248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003559807,"about_ca_topic_score_gemma":0.002860597,"domain_scores_codex":[0.9998846,0.00002628065,0.00000599866,0.00002959974,0.00003378131,0.00001984517],"domain_scores_gemma":[0.9997423,0.00009422938,0.00004635738,0.00002434963,0.00005787659,0.00003483692],"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":[0.00003042343,0.00004198394,0.0006387059,0.00003915715,0.000032376,0.0001292367,0.00004796889,0.90313,0.00269683,0.07727801,0.00161387,0.01432144],"study_design_scores_gemma":[0.00000857916,0.00001321724,0.00009527947,0.000002786627,0.000005506667,0.00002859373,0.000001656681,0.983503,0.0001373242,0.01549292,0.0007059007,0.000005219736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03858043,0.000505103,0.9398286,0.001400301,0.0002330018,0.00006042579,0.0001962325,0.0003160499,0.01887994],"genre_scores_gemma":[0.890851,0.000606249,0.08255624,0.0004268811,0.0001289809,0.0002636156,0.0001325378,0.00009606396,0.02493838],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003559807,"threshold_uncertainty_score":0.009201109,"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."}}