{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001688558,0.001099574,0.001165577,0.0006874039,0.0005608377,0.001052174,0.002751624,0.001226707,0.005386609],"category_scores_gemma":[0.005687376,0.000598675,0.000713178,0.0004568384,0.001125904,0.001880987,0.002006615,0.001799894,0.001100778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001128127,"about_ca_system_score_gemma":0.001498108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002618544,"about_ca_topic_score_gemma":0.003621663,"domain_scores_codex":[0.9989297,0.0003148904,0.00006236492,0.0002042782,0.0003848215,0.0001038833],"domain_scores_gemma":[0.9983029,0.0007714443,0.0001519032,0.0002621893,0.0003885812,0.0001229923],"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":[0.0001894272,0.0001495774,0.0008266749,0.0002589943,0.00009397227,0.0001327579,0.0001808584,0.5745934,0.002480498,0.2007016,0.008456803,0.2119353],"study_design_scores_gemma":[0.00002261327,0.00002920196,0.00005919015,0.000007855203,0.000009709608,0.00003343178,0.000005254221,0.9742023,0.0005401172,0.0216204,0.003459274,0.00001058325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003245099,0.0002210852,0.9911856,0.0001399604,0.00008848729,0.0000699779,0.00003736457,0.000518475,0.004493989],"genre_scores_gemma":[0.29504,0.0003950911,0.6914247,0.0002830343,0.0001178215,0.0005111451,0.0002010717,0.0001916293,0.01183543],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005386609,"threshold_uncertainty_score":0.01802003,"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."}}