{"id":"W2136602922","doi":"","title":"Incremental Natural Actor-Critic Algorithms","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":157,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Temporal difference learning; Computer science; Convergence (economics); Bellman equation; Mathematical proof; Function approximation; Algorithm; Variance (accounting); Stochastic gradient descent; Function (biology); Rate of convergence; Gradient descent; Artificial intelligence; Mathematical optimization; Mathematics; 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":[0.0004145986,0.000112992,0.00008987168,0.00009757355,0.0001014594,0.0001494115,0.0007321856,0.00004052903,0.00008062309],"category_scores_gemma":[0.00004699807,0.00009893506,0.00004740004,0.0002552347,0.00003730446,0.0005194405,0.0002901154,0.0001874801,0.000256017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008389457,"about_ca_system_score_gemma":0.00002457292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002857586,"about_ca_topic_score_gemma":0.000004931975,"domain_scores_codex":[0.9987401,0.00001686526,0.0002141265,0.0002287741,0.0004047999,0.000395323],"domain_scores_gemma":[0.9993472,0.0001023362,0.00004122898,0.0003587083,0.00005410389,0.00009643325],"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":[0.00002995878,0.0002255842,0.01542923,0.00007409385,0.0001885078,0.0004439936,0.002590696,0.01973543,0.03406189,0.6049364,0.0138956,0.3083886],"study_design_scores_gemma":[0.0009711609,0.0002446106,0.02680121,0.00002600254,0.000009391599,0.00009641339,0.0002391368,0.9171981,0.03734389,0.0005130997,0.01584345,0.0007135269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005854929,0.00003209087,0.9669248,0.0002226362,0.0009490399,0.00008605987,9.129278e-8,0.0003007263,0.02562956],"genre_scores_gemma":[0.8444117,0.000001909523,0.1520291,0.0007286769,0.00009362788,9.049734e-7,0.000001791353,0.000006404874,0.002725915],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8974627,"threshold_uncertainty_score":0.4034455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01335400574327761,"score_gpt":0.2696630519567899,"score_spread":0.2563090462135123,"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."}}