{"id":"W2094387729","doi":"10.1016/j.automatica.2009.07.008","title":"Natural actor–critic algorithms","year":2009,"lang":"en","type":"article","venue":"Automatica","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":569,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Temporal difference learning; Reinforcement learning; Computer science; Function approximation; Convergence (economics); Bellman equation; Mathematical proof; Function (biology); Stochastic gradient descent; Variance (accounting); Mathematics; Mathematical optimization; Artificial intelligence; Applied mathematics; Algorithm; Artificial neural network","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":[0.000140243,0.0001259981,0.0001392311,0.00007468036,0.000102602,0.0002203867,0.0008319107,0.00004454845,0.00003426801],"category_scores_gemma":[0.0001332536,0.0001118786,0.00005637345,0.0002688565,0.00002844921,0.0004764191,0.00009320102,0.0001742394,0.0004491799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004210856,"about_ca_system_score_gemma":0.00003856831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000159756,"about_ca_topic_score_gemma":9.431805e-8,"domain_scores_codex":[0.9988358,0.00003611151,0.0002227011,0.0002165021,0.0003569981,0.000331858],"domain_scores_gemma":[0.9991421,0.0001027287,0.00005806637,0.0005655764,0.000048424,0.00008314654],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004362511,0.0002060781,0.0002340662,0.0000800835,0.00009036154,0.0002083638,0.003729093,0.03878931,0.004153063,0.5334502,0.01907304,0.399982],"study_design_scores_gemma":[0.000156992,0.0001033798,0.007838191,0.00002352456,0.00000489476,0.00002317627,0.000008011419,0.9865984,0.0004123057,0.002861236,0.001803989,0.0001659013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002371119,0.00006220524,0.9814356,0.003212282,0.0005603607,0.0001228167,1.51954e-7,0.0008934062,0.01134205],"genre_scores_gemma":[0.8310422,0.000002862118,0.1666463,0.00123374,0.00005489538,0.000002312721,0.000001650235,0.000005339909,0.001010732],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9478091,"threshold_uncertainty_score":0.5773448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009214446772915929,"score_gpt":0.2557505181836024,"score_spread":0.2465360714106865,"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."}}