{"id":"W4210732917","doi":"10.1016/bs.hna.2021.12.016","title":"Machine learning and control theory","year":2022,"lang":"en","type":"book-chapter","venue":"Handbook of numerical analysis","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Chinese University of Hong Kong; Saint Mary’s University; National Science Foundation","keywords":"Computer science; Artificial intelligence; Machine learning; Online machine learning; Algorithmic learning theory; Reinforcement learning; Computational learning theory; Control (management); Stochastic gradient descent; Probably approximately correct learning; Field (mathematics); Active learning (machine learning); Artificial neural network; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004535497,0.0003100582,0.0009388888,0.0005216478,0.000190887,0.00006653291,0.0006336044,0.0001221501,0.003049553],"category_scores_gemma":[0.00007624731,0.0002827586,0.0005099897,0.0002552017,0.0001337886,0.000109772,0.0005239309,0.000661825,0.0000288459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005321327,"about_ca_system_score_gemma":0.00004000252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002370935,"about_ca_topic_score_gemma":7.882499e-7,"domain_scores_codex":[0.9979336,0.0001443377,0.0005177187,0.0005272256,0.00064432,0.0002328015],"domain_scores_gemma":[0.9981834,0.0005256181,0.0005913981,0.0004955454,0.00007950972,0.0001245848],"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":[0.00006098266,0.00003434046,0.002092978,0.00007902146,0.00847127,0.00006741024,0.0003712403,0.4372192,0.00004834439,0.5180634,0.0001072438,0.03338457],"study_design_scores_gemma":[0.000519766,0.0003667542,0.0000472152,0.00005626806,0.00272824,0.000008493557,0.000005157456,0.791121,0.00001231503,0.006524919,0.1980857,0.0005241477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[3.791339e-7,0.004633386,0.8963783,0.00009218919,0.00004673647,0.00009639161,0.000007254764,0.00008068312,0.09866469],"genre_scores_gemma":[0.0585654,0.005305103,0.02760114,0.0006756119,0.0001173302,0.00002658533,0.0001506021,0.0001101819,0.9074481],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8687772,"threshold_uncertainty_score":0.9999624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009157608706874624,"score_gpt":0.2191808153626343,"score_spread":0.2100232066557597,"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."}}