{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001222539,0.0006786848,0.001015868,0.0002830518,0.0003322829,0.0007910384,0.0010829,0.0009402533,0.001545449],"category_scores_gemma":[0.001922552,0.0003515551,0.0004083157,0.0003309466,0.000932111,0.0006380819,0.001023642,0.001090561,0.0002105437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007607275,"about_ca_system_score_gemma":0.0008945913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00686659,"about_ca_topic_score_gemma":0.003915695,"domain_scores_codex":[0.999598,0.000132514,0.00002042715,0.00007984018,0.0001197582,0.00004959915],"domain_scores_gemma":[0.9991707,0.00040296,0.0001300157,0.00004073793,0.000219096,0.00003654659],"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":[0.00007750303,0.00004071545,0.0002279459,0.00008733974,0.00003909873,0.00006549009,0.00006554434,0.9629554,0.002031457,0.008911581,0.0005427493,0.02495515],"study_design_scores_gemma":[0.000005627575,0.00002148749,0.00003704676,0.000002516342,0.000002708594,0.000004493597,0.00000165958,0.9990084,0.000122385,0.0006866636,0.0001044395,0.000002628165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01627552,0.0004090656,0.980071,0.0002734615,0.00008642861,0.00002700165,0.00001699233,0.0001559849,0.002684662],"genre_scores_gemma":[0.9682903,0.0001776172,0.02857843,0.00009893325,0.00005847904,0.00008551685,0.00002846515,0.00002277078,0.002659363],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00686659,"threshold_uncertainty_score":0.01365328,"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."}}