{"id":"W2083748997","doi":"10.1007/s11768-011-0170-8","title":"Asymptotic tracking by a reinforcement learning-based adaptive critic controller","year":2011,"lang":"en","type":"article","venue":"Journal of Control Theory and Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Control theory (sociology); Controller (irrigation); Reinforcement learning; Artificial neural network; Tracking error; Computer science; Feed forward; Bounded function; Adaptive control; Nonlinear system; Lyapunov function; Lyapunov stability; Mathematics; Artificial intelligence; Control engineering; Engineering; Control (management)","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":[0.0009457591,0.0006158239,0.0008139966,0.0003689983,0.0004313576,0.0007652216,0.001065443,0.001248297,0.00191177],"category_scores_gemma":[0.002619898,0.0003631905,0.0003897452,0.0002637063,0.0007593481,0.0005146516,0.0009178896,0.001200223,0.000502574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005234191,"about_ca_system_score_gemma":0.0007896974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005257497,"about_ca_topic_score_gemma":0.003693469,"domain_scores_codex":[0.9996945,0.00008694072,0.00001549192,0.00006577536,0.0001031244,0.00003428191],"domain_scores_gemma":[0.9992326,0.0003225623,0.00007719813,0.00006702799,0.0002565582,0.00004398093],"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":[0.0002145753,0.0001119829,0.0006321942,0.000104205,0.00008313947,0.0001870533,0.00009785877,0.8949131,0.01334222,0.01443332,0.001796924,0.07408335],"study_design_scores_gemma":[0.00001834166,0.00003330024,0.00006312686,0.000003502711,0.00000610385,0.00001779573,0.000001832743,0.998566,0.0003516537,0.0007325963,0.0002010072,0.000004739935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0244796,0.0002533188,0.9677143,0.0002708392,0.0001734089,0.00004312147,0.00001172121,0.0005170213,0.006536722],"genre_scores_gemma":[0.9399233,0.0001485657,0.05478798,0.0001217038,0.00007030233,0.0001157994,0.00002437276,0.00004447842,0.004763474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005257497,"threshold_uncertainty_score":0.01045376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01146694965448446,"score_gpt":0.2295948023311984,"score_spread":0.2181278526767139,"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."}}