{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002061497,0.000109146,0.0001191979,0.00008694357,0.0001067789,0.0000313736,0.0000721245,0.00005626978,0.000004389521],"category_scores_gemma":[0.00002442144,0.0001159784,0.0000654629,0.0001880008,0.000003056204,0.0003248924,0.000006816133,0.00005767233,0.0000161926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001078336,"about_ca_system_score_gemma":0.0000128164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008705196,"about_ca_topic_score_gemma":0.0000121712,"domain_scores_codex":[0.9992473,0.00001063829,0.0002113389,0.000141522,0.0001224192,0.0002667761],"domain_scores_gemma":[0.9997202,0.00002810784,0.00002690991,0.0001418254,0.00003446839,0.00004844447],"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":[0.000003973887,0.000002364643,0.00004722842,0.00005837104,0.00001324913,2.407427e-7,0.000063624,0.9788231,0.01957646,0.0003300465,0.00006881435,0.001012483],"study_design_scores_gemma":[0.0006279621,0.00005073569,0.00001211362,0.00002769911,0.00001000711,7.352202e-8,0.00002441464,0.997895,0.0007475322,0.0001268905,0.0003313578,0.0001461944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005660104,0.00001791161,0.9907892,0.00002822522,0.0001659321,0.0005572445,8.867217e-7,0.002019284,0.0007611662],"genre_scores_gemma":[0.9739571,0.000002908213,0.02463143,0.00001587158,0.00003934214,0.0003062675,0.0001490212,0.00004944513,0.0008486459],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9682969,"threshold_uncertainty_score":0.4729462,"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."}}