{"id":"W2943366292","doi":"10.1038/s42256-019-0053-0","title":"Moving beyond reward prediction errors","year":2019,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"The Scarborough Hospital; Canadian Institute for Advanced Research; University of Toronto; Vector Institute","funders":"","keywords":"Business; Computer science","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":[0.0004315875,0.0002157842,0.0001853639,0.0001871993,0.000105208,0.000157589,0.001469097,0.00027887,0.0001545805],"category_scores_gemma":[0.0002241968,0.0001936553,0.00009174016,0.0006065228,0.00003612344,0.0005995479,0.0004211563,0.001283348,0.0006851373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009324714,"about_ca_system_score_gemma":0.00005501392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002335904,"about_ca_topic_score_gemma":0.000003502142,"domain_scores_codex":[0.9980791,0.00006047031,0.0003420321,0.0005345851,0.0006197447,0.0003640285],"domain_scores_gemma":[0.9985601,0.0001514189,0.0001581677,0.0009036337,0.0001278161,0.00009888591],"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":[0.00001521733,0.00003288776,0.02524105,0.00005987663,0.00004002159,0.00001811082,0.0008365958,0.8344966,0.0009155343,0.09966774,0.001255005,0.0374214],"study_design_scores_gemma":[0.0000841907,0.0001756393,0.002742467,0.00005419695,0.000007062095,0.00003334364,0.00002912844,0.9756142,0.005417157,0.002659484,0.01291193,0.0002711838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004325849,0.0004596941,0.9710661,0.0007147132,0.002602294,0.0002685733,0.000002573368,0.0004042892,0.02015588],"genre_scores_gemma":[0.9645901,0.00004161673,0.03104098,0.0008933728,0.0001111227,0.000005393972,0.00001172287,0.00001849287,0.003287183],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9602643,"threshold_uncertainty_score":0.8806283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006224225736806918,"score_gpt":0.2522100027226873,"score_spread":0.2459857769858804,"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."}}