{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006152695,0.0004964893,0.0004514715,0.0001454879,0.0001986572,0.0006302915,0.0009174406,0.0008008311,0.002255552],"category_scores_gemma":[0.002958454,0.0003194158,0.000265088,0.0001831976,0.0007630159,0.001261916,0.00100561,0.00167081,0.0004367559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006054216,"about_ca_system_score_gemma":0.0005966921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001675644,"about_ca_topic_score_gemma":0.002015417,"domain_scores_codex":[0.9998602,0.00004107579,0.000006764923,0.00003150745,0.00004026671,0.00002018391],"domain_scores_gemma":[0.9991395,0.0005018876,0.0001073555,0.0001273719,0.00007718335,0.00004666288],"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":[0.00007146326,0.00005573701,0.0006849376,0.00008211999,0.00002989095,0.00007229482,0.0000571627,0.9089891,0.01019032,0.03479873,0.001071146,0.04389704],"study_design_scores_gemma":[0.000006902977,0.00001959566,0.00005637177,0.000003945348,0.000002494577,0.00001015989,0.000004070963,0.9901636,0.001034373,0.008323771,0.0003717809,0.000002784688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04786962,0.0001813438,0.9460495,0.0003591634,0.00006042785,0.00004000419,0.00005909947,0.0007376635,0.004643292],"genre_scores_gemma":[0.8822547,0.0001309887,0.1154335,0.0001217061,0.00002000538,0.00008800981,0.00008012605,0.00007018066,0.00180076],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002255552,"threshold_uncertainty_score":0.00754559,"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."}}