{"id":"W4402262825","doi":"10.23919/acc60939.2024.10644360","title":"A Practical Reinforcement Learning (RL) Controller Design for Nonlinear Systems","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Reinforcement learning; Computer science; Nonlinear system; Controller (irrigation); Reinforcement; Control theory (sociology); Control engineering; Artificial intelligence; Engineering; Control (management); Structural engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0003142697,0.0001415911,0.0002042872,0.00007565894,0.00004949043,0.0001431794,0.00004435666,0.00007926219,0.00002149782],"category_scores_gemma":[0.0001493162,0.0001223734,0.00005991941,0.0001038295,0.00000719082,0.0002580195,0.000008076335,0.0001376421,0.00008873991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001266471,"about_ca_system_score_gemma":0.00002616862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004474772,"about_ca_topic_score_gemma":4.855589e-7,"domain_scores_codex":[0.9991141,0.00003259426,0.0003082547,0.0001653094,0.0001352611,0.000244492],"domain_scores_gemma":[0.99931,0.0004506209,0.0000222453,0.00009206463,0.00006533528,0.00005972394],"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":[0.00002766394,0.000002738286,6.408045e-7,0.0001639182,0.00009948134,0.000004248356,0.00004337344,0.9870803,0.0009865183,0.008271376,0.002754912,0.0005647769],"study_design_scores_gemma":[0.0005688715,0.00007156759,1.305869e-7,0.00006840393,0.00003158641,0.00001347257,0.0000718817,0.9299429,0.0001764935,0.00002642181,0.06889096,0.000137293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00001146273,0.0007543592,0.9929979,0.0001001804,0.0006709934,0.001164415,0.000001779523,0.001154723,0.003144198],"genre_scores_gemma":[0.8689491,0.00005571356,0.1218512,0.00002663273,0.0005406907,0.0007883176,0.0000222044,0.0001047674,0.007661353],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8711467,"threshold_uncertainty_score":0.4990241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02457321598695149,"score_gpt":0.2777408226012688,"score_spread":0.2531676066143173,"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."}}