{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008569007,0.0005482095,0.0006304831,0.0002342497,0.0003644978,0.0009373579,0.0008466783,0.0005385019,0.001474345],"category_scores_gemma":[0.001586707,0.0002148148,0.0004767712,0.0003110544,0.0009400151,0.0006095852,0.0008362039,0.00100847,0.0001834815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008938646,"about_ca_system_score_gemma":0.001097332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007307277,"about_ca_topic_score_gemma":0.003024358,"domain_scores_codex":[0.9996486,0.00005938092,0.00001813546,0.0000968123,0.0001264033,0.00005070698],"domain_scores_gemma":[0.9994569,0.0002185651,0.0001064622,0.00004536203,0.0001430351,0.00002952113],"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":[0.0001043258,0.00005096796,0.0004319195,0.0001032714,0.00003420838,0.0001002941,0.00007414076,0.9284812,0.007667816,0.02095336,0.0008143002,0.04118409],"study_design_scores_gemma":[0.000004475285,0.0000200412,0.00005495486,0.000002766899,0.000003148534,0.000007324751,0.000002633068,0.9974586,0.0007719955,0.001490355,0.0001802916,0.000003404796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01863395,0.000118173,0.9777806,0.0001226985,0.0000260492,0.00002886424,0.00002316561,0.0001781587,0.003088218],"genre_scores_gemma":[0.962685,0.0001007241,0.03542041,0.00005218734,0.00001671159,0.00004556687,0.00003714823,0.00002136073,0.001620743],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007307277,"threshold_uncertainty_score":0.01452953,"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."}}