{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000612983,0.0002546371,0.0003243318,0.0001359411,0.0001219506,0.0001620355,0.00147472,0.0000889181,0.00001685804],"category_scores_gemma":[0.00007606505,0.0002157877,0.0001400373,0.000253559,0.00005346028,0.0007300015,0.00056512,0.0003914765,0.000068735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002172557,"about_ca_system_score_gemma":0.0001350332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009600831,"about_ca_topic_score_gemma":0.000003224837,"domain_scores_codex":[0.9979759,0.0001206891,0.0003098425,0.0005789577,0.0004531024,0.0005615427],"domain_scores_gemma":[0.9985558,0.0001016832,0.0001609923,0.0008985621,0.0001612198,0.0001217413],"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":[0.00002824684,0.00002577237,0.000245617,0.000004194841,0.00005044473,0.000001837856,0.0002550575,0.6946893,0.0004838618,0.2974132,0.00002556338,0.006776927],"study_design_scores_gemma":[0.001681494,0.0001836106,0.00002819925,0.00001251599,0.00001347954,0.000009463589,0.0001375514,0.995307,0.00002826526,0.002212422,0.0001061606,0.0002798433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002614184,0.00003151079,0.9728317,0.0001091437,0.0001339505,0.0006374713,6.370778e-7,0.0003686634,0.02327275],"genre_scores_gemma":[0.6909654,4.516478e-7,0.3063436,0.0002437929,0.00002241855,0.00001920923,0.000001622788,0.00001356985,0.002389878],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6883512,"threshold_uncertainty_score":0.8799568,"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."}}