{"id":"W7064595611","doi":"","title":"Biologically-Based Neural Representations Enable Fast Online Shallow Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"NPARC","topic":"Magnetic confinement fusion research","field":"Physics and Astronomy","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Task (project management); Representation (politics); Artificial neural network; Grid; Deep learning; Simple (philosophy); Feature learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001777076,0.00009416988,0.0001055059,0.00007624364,0.0004233999,0.00003907915,0.0002349164,0.0000104219,0.6752477],"category_scores_gemma":[0.00001832891,0.00008861356,0.0000762301,0.0002228201,0.00003499286,0.00001220436,0.0003278188,0.0003298926,0.00003472471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000127379,"about_ca_system_score_gemma":0.00007757761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003837842,"about_ca_topic_score_gemma":0.000009769338,"domain_scores_codex":[0.9988087,0.0001255622,0.0002044961,0.0002377326,0.0003440316,0.0002794519],"domain_scores_gemma":[0.9994915,0.00009252481,0.0000666558,0.0002190883,0.00005189644,0.00007839551],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000161068,0.001037708,0.1275553,0.00002365903,0.00008354004,0.00002575488,0.0003536914,0.1818501,0.1298978,0.01560273,0.03652543,0.5068832],"study_design_scores_gemma":[0.001651209,0.0006611795,0.007564061,0.00000572122,0.00001853452,6.689907e-7,0.003465998,0.5906946,0.001113264,0.0008443497,0.3936782,0.0003021672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4456053,0.000006819422,0.002576473,0.00800706,0.0001174532,0.0005762888,0.00004884077,0.00008288366,0.5429789],"genre_scores_gemma":[0.9691794,6.089029e-7,0.0007612511,0.0002126649,0.000087566,0.0002118749,0.0005062179,0.000007579052,0.02903286],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6752129,"threshold_uncertainty_score":0.3613556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0231411415193142,"score_gpt":0.2815751297181558,"score_spread":0.2584339881988417,"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."}}