{"id":"W2972894795","doi":"10.1101/764969","title":"Learning action-oriented models through active inference","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Embodied and Extended Cognition","field":"Neuroscience","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Biotechnology and Biological Sciences Research Council; University of Sussex; Canadian Institute for Advanced Research","keywords":"Computer science; Inference; Exploit; Action (physics); Artificial intelligence; Machine learning; Probabilistic logic; Process (computing); Representation (politics); Convergence (economics); Reinforcement learning; Graphical model","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002522333,0.0006770471,0.0005891265,0.000251902,0.0004049899,0.0002730918,0.000624655,0.0006633469,0.00007785876],"category_scores_gemma":[0.001073454,0.0007435751,0.0002033913,0.0006221738,0.0001705686,0.001003215,0.0006879246,0.002202246,0.0005276561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003588496,"about_ca_system_score_gemma":0.0006204015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000622755,"about_ca_topic_score_gemma":0.000001331536,"domain_scores_codex":[0.9959739,0.0003524484,0.000502883,0.001724251,0.0006784075,0.0007681297],"domain_scores_gemma":[0.9973187,0.0003037339,0.0006115483,0.001079443,0.0004845753,0.0002020179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001600295,0.0002834646,0.0003888262,0.0004410015,0.0000801539,0.00006153865,0.0001523497,0.0140715,0.9058825,0.07833651,0.000120734,0.00002143875],"study_design_scores_gemma":[0.0007274504,0.0001356078,0.001100114,0.0006203767,0.0001139323,3.804287e-8,0.00003018348,0.01725473,0.9743028,0.001218635,0.003149283,0.001346896],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9405841,0.0002334412,0.03915929,0.0003534259,0.006749794,0.002291184,0.0004958762,0.002696711,0.007436174],"genre_scores_gemma":[0.9968721,0.0007590688,0.001120673,0.0004640623,0.00039384,0.0002107446,7.080327e-7,0.0001433645,0.00003538642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07711787,"threshold_uncertainty_score":0.9995015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05150532497094573,"score_gpt":0.2757388789338975,"score_spread":0.2242335539629517,"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."}}