{"id":"W4324137886","doi":"10.1016/j.engappai.2023.106029","title":"Real-time measurement-driven reinforcement learning control approach for uncertain nonlinear systems","year":2023,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Extremum Seeking Control Systems","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Payload (computing); Robustness (evolution); Nonlinear system; Control theory (sociology); Benchmark (surveying); Process (computing); Overshoot (microwave communication); Mathematical optimization; Artificial intelligence; Control (management); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007805221,0.0002471078,0.0003894956,0.0003135887,0.000107028,0.00005783579,0.0003674093,0.000116512,0.000004971282],"category_scores_gemma":[0.0001540821,0.0002818476,0.00012393,0.0007270498,0.00003201211,0.00008352894,0.00002441572,0.0001728364,0.0001142011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000183312,"about_ca_system_score_gemma":0.00002610574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006940087,"about_ca_topic_score_gemma":0.000001363066,"domain_scores_codex":[0.9980546,0.00002378187,0.00078707,0.0002979297,0.0004031902,0.0004334221],"domain_scores_gemma":[0.9988285,0.0002410365,0.0001196695,0.0004306518,0.0002813514,0.00009875813],"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":[0.000007343222,0.00001429819,0.000007436429,0.0002828306,0.00007730928,2.316222e-7,0.0001086554,0.7759821,0.2190022,0.002865272,0.00007710128,0.001575261],"study_design_scores_gemma":[0.00007363123,0.00004155668,0.000005403514,0.00006846747,0.00003558539,0.000001313481,0.0001638641,0.9925364,0.004520399,0.0000371186,0.002266584,0.0002497247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007900674,0.0001311111,0.9952609,0.00001717949,0.0001813989,0.001697736,0.00002339181,0.001335653,0.0005625733],"genre_scores_gemma":[0.9861816,0.00004583412,0.01102244,0.000001367788,0.0003297199,0.002122679,0.0000846304,0.00009095005,0.0001208209],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9853915,"threshold_uncertainty_score":0.9999633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03178531760799076,"score_gpt":0.2511181779017388,"score_spread":0.2193328602937481,"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."}}