{"id":"W2903618924","doi":"10.1002/acs.2949","title":"A set‐based model‐free reinforcement learning design technique for nonlinear systems","year":2018,"lang":"en","type":"article","venue":"International Journal of Adaptive Control and Signal Processing","topic":"Extremum Seeking Control Systems","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Phasor; Reinforcement learning; Control theory (sociology); Nonlinear system; Controller (irrigation); Optimal control; Set (abstract data type); Computer science; Mathematical optimization; Bellman equation; Class (philosophy); Mathematics; Control (management); Artificial intelligence; Electric power system; Power (physics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001010609,0.000544212,0.0006351031,0.0002753067,0.0003330215,0.0004333243,0.0008079092,0.0006561846,0.002058259],"category_scores_gemma":[0.001307592,0.0003740469,0.0005577495,0.0001656027,0.0006005184,0.000411461,0.0007623099,0.001208609,0.0003355479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005036365,"about_ca_system_score_gemma":0.000530418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002427809,"about_ca_topic_score_gemma":0.001637358,"domain_scores_codex":[0.9996952,0.0001224831,0.00001225551,0.00004234105,0.0001049559,0.00002278585],"domain_scores_gemma":[0.9995987,0.0001970423,0.00004937021,0.00003171213,0.0001072908,0.0000160347],"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":[0.00003854804,0.00003458325,0.0001493249,0.00006017987,0.00003791518,0.00004243242,0.00006801471,0.9374474,0.004959888,0.01552155,0.0005257707,0.04111442],"study_design_scores_gemma":[0.000004167654,0.00002253833,0.00001754534,0.000003734767,0.00000286375,0.000005612626,0.000001273222,0.9981074,0.0003214223,0.001223887,0.0002873144,0.000002228637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003962664,0.0000684343,0.9945138,0.00005641306,0.00001595943,0.00001505939,0.00000348344,0.00009787422,0.001266344],"genre_scores_gemma":[0.834901,0.0001524381,0.1605164,0.0001060491,0.00003782435,0.0002293735,0.00002503282,0.00004354951,0.003988529],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002427809,"threshold_uncertainty_score":0.006885588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02593868401802293,"score_gpt":0.2556496466587131,"score_spread":0.2297109626406902,"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."}}