{"id":"W4324130748","doi":"10.1002/rnc.6662","title":"Robust <i>H</i><sub>∞</sub> tracking of linear <scp>discrete‐time</scp> systems using <scp>Q‐learning</scp>","year":2023,"lang":"en","type":"article","venue":"International Journal of Robust and Nonlinear Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Algebraic Riccati equation; Riccati equation; Bounded function; Algebraic number; Tracking (education); Control theory (sociology); Mathematics; Reinforcement learning; Discrete time and continuous time; Robust control; Norm (philosophy); Robustness (evolution); Stability (learning theory); Mathematical optimization; Computer science; Control system; Control (management); Differential equation; Artificial intelligence; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001780951,0.0003646261,0.0007871382,0.0007672474,0.0001880843,0.0004023935,0.001419273,0.0001963611,0.000001182738],"category_scores_gemma":[0.002051373,0.0003334544,0.0003807713,0.0006014421,0.0001557719,0.0009952036,0.0002905435,0.0007252074,0.00002552414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001320855,"about_ca_system_score_gemma":0.0002821614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002473665,"about_ca_topic_score_gemma":0.000003676791,"domain_scores_codex":[0.9961941,0.0003121368,0.001220298,0.0004340117,0.001275112,0.0005643888],"domain_scores_gemma":[0.9942394,0.001834782,0.001542662,0.0002734757,0.001843671,0.0002659801],"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":[0.00007427578,0.0002538802,0.007924925,0.00007120397,0.001646477,0.0008181699,0.001305347,0.871994,0.09306765,0.001150787,0.0006485199,0.02104479],"study_design_scores_gemma":[0.002979056,0.0002979379,0.001076294,0.0003175282,0.0001052281,0.0005115019,0.000315492,0.9897187,0.001995116,0.00008038312,0.002511136,0.00009160081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4185947,0.0008367613,0.5785225,0.0002270913,0.001334533,0.0002444866,0.00003768768,0.0001113234,0.00009090869],"genre_scores_gemma":[0.9773732,0.0001948685,0.02053696,0.0001139645,0.001492861,0.000006428266,0.00001732093,0.0000586855,0.0002056771],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5587785,"threshold_uncertainty_score":0.9999117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02227317367211629,"score_gpt":0.250750505202805,"score_spread":0.2284773315306887,"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."}}