{"id":"W4402305461","doi":"10.1016/j.ifacol.2024.08.449","title":"A Deep Reinforcement Learning-Based PID Tuning Strategy for Nonlinear MIMO Systems with Time-varying Uncertainty","year":2024,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Advanced Control Systems Design","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; PID controller; Nonlinear system; MIMO; Control theory (sociology); Computer science; Reinforcement; Control engineering; Artificial intelligence; Engineering; Psychology; Physics; Control (management); Telecommunications; Social psychology; Temperature control","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":[0.0003404053,0.0004992544,0.0005629021,0.0001978538,0.0001678874,0.0002204751,0.000228709,0.0001670882,0.00005735961],"category_scores_gemma":[0.00005752065,0.0004307194,0.0001579705,0.0003613863,0.00004491201,0.0002577631,0.0000179676,0.0004470666,0.0001061815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003783431,"about_ca_system_score_gemma":0.0001284138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005865841,"about_ca_topic_score_gemma":0.00002846451,"domain_scores_codex":[0.9977782,0.00006012397,0.0005574625,0.0005082552,0.0003757532,0.0007201941],"domain_scores_gemma":[0.9988499,0.000405106,0.00008808467,0.000340437,0.0001266608,0.000189818],"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":[0.0001209928,0.00001362643,0.00000805405,0.001077791,0.0002424156,0.00006529075,0.0001912574,0.9833348,0.01171672,0.00007067218,0.00001088408,0.003147533],"study_design_scores_gemma":[0.00141742,0.0004644988,0.000001288391,0.0007725502,0.0001067363,0.00003135697,0.0002674977,0.9884607,0.0003299132,0.000005388046,0.007604457,0.0005381905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002410349,0.005101451,0.9870451,0.0001131714,0.0005131331,0.00148534,0.0000396746,0.001887401,0.001404363],"genre_scores_gemma":[0.9237418,0.0000344511,0.07109542,0.00007411951,0.001040922,0.0005129451,0.0004907576,0.000308404,0.002701147],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9213315,"threshold_uncertainty_score":0.9998145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01324766589085903,"score_gpt":0.2349124473748849,"score_spread":0.2216647814840259,"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."}}