{"id":"W2967692091","doi":"10.1109/rose.2019.8790432","title":"Model-Free Adaptive Control Approach Using Integral Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Adaptive control; Control (management); Reinforcement; 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":[0.0007166868,0.0005927176,0.0006670687,0.0002920562,0.0003111025,0.0008450706,0.001017421,0.0006441572,0.001699641],"category_scores_gemma":[0.0009992946,0.0002190484,0.0004452729,0.0002599427,0.000738133,0.0006358905,0.0009723743,0.001200036,0.0002588994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005662501,"about_ca_system_score_gemma":0.0008498127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003513239,"about_ca_topic_score_gemma":0.001944964,"domain_scores_codex":[0.9996449,0.00007363674,0.00001475055,0.0000765652,0.0001509243,0.0000392797],"domain_scores_gemma":[0.999653,0.0001368625,0.00005310686,0.00004050681,0.00009802495,0.00001839603],"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":[0.00004740382,0.00006701287,0.0002818134,0.00007498933,0.00004824708,0.00007555874,0.00008490615,0.9024934,0.005282664,0.02717608,0.0006729133,0.06369495],"study_design_scores_gemma":[0.000004393478,0.00002476521,0.00002989175,0.000002438092,0.000003962649,0.000009567791,0.000001856413,0.9972409,0.0004335401,0.001915568,0.0003300335,0.000003140908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00596163,0.0001171255,0.9905875,0.00006861697,0.00002693049,0.00002328298,0.000006538207,0.00017137,0.003037059],"genre_scores_gemma":[0.9168585,0.0001856221,0.07899725,0.00009883216,0.00004556255,0.0001202828,0.00002834574,0.00003263776,0.003633007],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003513239,"threshold_uncertainty_score":0.006985605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02325165548238078,"score_gpt":0.2321184257896034,"score_spread":0.2088667703072226,"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."}}