{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003053341,0.0005417358,0.001142246,0.0002891295,0.0001100493,0.00012794,0.002812886,0.0004438805,0.00001357143],"category_scores_gemma":[0.0002298193,0.0006111325,0.000444178,0.0005599749,0.0002344522,0.0001906857,0.0008434862,0.001193287,0.0000491246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002195844,"about_ca_system_score_gemma":0.0004761648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002183448,"about_ca_topic_score_gemma":0.00001448917,"domain_scores_codex":[0.9968293,0.0005108036,0.0005054756,0.001417539,0.0002325191,0.0005044151],"domain_scores_gemma":[0.9964852,0.0003463005,0.001028134,0.001290952,0.0005677759,0.000281595],"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":[0.00018605,0.0001737332,0.002546174,0.0001855855,0.0004141234,0.0003904414,0.0000967352,0.9786572,0.0006937527,0.01579931,0.00003806483,0.0008187682],"study_design_scores_gemma":[0.002336646,0.000273945,0.0005409446,0.0001370638,0.0001799311,0.000003189292,0.00004250679,0.9941083,0.00004934778,0.00105832,0.0007489373,0.0005208449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05664685,0.000138267,0.9407126,0.0002110011,0.0004947498,0.0008703814,0.0002220931,0.0005834918,0.0001205187],"genre_scores_gemma":[0.9941518,0.000007900905,0.004874879,0.0001043967,0.0001401797,0.000001906361,0.0001248514,0.00004309898,0.0005509765],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9375049,"threshold_uncertainty_score":0.999634,"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."}}