{"id":"W4391020458","doi":"10.1109/cdc49753.2023.10384059","title":"An Observer-Based Reinforcement Learning Solution for Model-Following Problems","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Reinforcement learning; Computer science; Observer (physics); Trajectory; Control theory (sociology); Process (computing); Projection (relational algebra); Key (lock); Artificial intelligence; Tracking (education); Tracking error; Control (management); Algorithm","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":[0.0007520732,0.0006176488,0.0007154925,0.0002136077,0.0002639055,0.0005707015,0.000937931,0.001018445,0.001579187],"category_scores_gemma":[0.001618503,0.0002760823,0.0004077709,0.0001689898,0.0005679611,0.000593449,0.0008349144,0.001227038,0.0002855569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004187288,"about_ca_system_score_gemma":0.00100471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002546977,"about_ca_topic_score_gemma":0.00210978,"domain_scores_codex":[0.9997303,0.00007800026,0.00001254765,0.00004692616,0.0001054572,0.00002680216],"domain_scores_gemma":[0.9996363,0.0001604367,0.00006120235,0.00002550639,0.00009469095,0.00002177773],"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":[0.00004173313,0.00004199083,0.000204231,0.00008491333,0.00002465493,0.00007298656,0.00006496489,0.9286572,0.004005653,0.03112652,0.0008239455,0.0348512],"study_design_scores_gemma":[0.000007874401,0.00002344888,0.00002255358,0.000003330955,0.000002353358,0.000007938933,0.00000190386,0.9970915,0.0002952808,0.002086467,0.0004546079,0.000002635756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002345171,0.00005442216,0.9962751,0.000060974,0.00002122143,0.00001286894,0.000006523702,0.00009374152,0.001130099],"genre_scores_gemma":[0.7451866,0.000259529,0.2475685,0.0001135917,0.00007533667,0.0002842158,0.00007951828,0.00006162243,0.006371125],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002546977,"threshold_uncertainty_score":0.005282938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02602351320742093,"score_gpt":0.2499376867377831,"score_spread":0.2239141735303622,"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."}}