{"id":"W3093727384","doi":"10.48550/arxiv.2010.10577","title":"Structured Online Learning-based Control of Continuous-time Nonlinear Systems","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Bellman equation; Parameterized complexity; Benchmark (surveying); Optimal control; Bounded function; Nonlinear system; Mathematical optimization; Function (biology); Mathematics; Algorithm; Artificial intelligence","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":[0.0008599783,0.0007727864,0.0008696102,0.0002950232,0.0003194444,0.0008533046,0.0007983997,0.0007652708,0.001306252],"category_scores_gemma":[0.001971567,0.0003350664,0.0004110748,0.000315069,0.0009729304,0.0005381862,0.0008506342,0.001147274,0.0001940425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006856237,"about_ca_system_score_gemma":0.001006015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007347673,"about_ca_topic_score_gemma":0.004507967,"domain_scores_codex":[0.9995838,0.0001419611,0.00001890428,0.00008498724,0.0001219668,0.00004825785],"domain_scores_gemma":[0.9991097,0.0005512957,0.0001092313,0.00005360317,0.0001468839,0.00002926848],"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":[0.00002911679,0.00002393924,0.0001120091,0.00003819319,0.00001395498,0.00002381872,0.00002316786,0.9825475,0.0008475856,0.003911254,0.0002041035,0.01222536],"study_design_scores_gemma":[0.000003765345,0.00001235386,0.00002018711,0.000001817185,0.000001200113,0.00000188668,9.894225e-7,0.9989618,0.0001384044,0.0007940996,0.00006244001,0.000001017333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0208643,0.000292413,0.9752156,0.0001756312,0.00005462116,0.00003558598,0.00002350995,0.0003157243,0.003022713],"genre_scores_gemma":[0.9674394,0.0001710126,0.03060839,0.00005454341,0.00003393745,0.000106448,0.00005335517,0.00002729834,0.001505708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007347673,"threshold_uncertainty_score":0.01460981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0276682652161334,"score_gpt":0.1773092218835637,"score_spread":0.1496409566674304,"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."}}