{"id":"W3017059342","doi":"10.1049/iet-cta.2019.0397","title":"Integral reinforcement learning solutions for a synchronisation system with constrained policies","year":2020,"lang":"en","type":"article","venue":"IET Control Theory and Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Control theory (sociology); Control engineering; Mathematical optimization; Artificial intelligence; Mathematics; Control (management); 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":[0.000467989,0.0001329315,0.0001769016,0.0000384057,0.000543982,0.000130182,0.0002663933,0.00003981703,0.000001400919],"category_scores_gemma":[0.00006866222,0.0001106979,0.00005050413,0.0001646576,0.0001698286,0.000181041,0.00005181142,0.0001164193,0.000005893216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005084676,"about_ca_system_score_gemma":0.000079829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008269843,"about_ca_topic_score_gemma":0.000002981557,"domain_scores_codex":[0.9990322,0.0001045772,0.0001963743,0.0002882205,0.00009909455,0.0002795137],"domain_scores_gemma":[0.9989837,0.0004552859,0.0001316971,0.0001931264,0.0001207828,0.0001153615],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007367753,0.00001076657,0.0000184386,0.00002478616,0.00005740223,2.945566e-7,0.0005078877,0.006374793,0.0005794927,0.9731149,0.000009163155,0.01922837],"study_design_scores_gemma":[0.002112427,0.0003829847,0.00005861438,0.0000264098,0.00006807625,0.00001440763,0.001288083,0.9820299,0.00002898531,0.007361385,0.006430553,0.0001981594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001853778,0.0001038063,0.994257,0.003063155,0.0000131704,0.001396475,0.00001346803,0.0003481127,0.0006194636],"genre_scores_gemma":[0.9918461,0.000002174814,0.005747834,0.0005489484,0.00009932485,0.001676296,0.00001396702,0.000009130045,0.00005619054],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9916608,"threshold_uncertainty_score":0.4514129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01138973012840052,"score_gpt":0.2271804721164862,"score_spread":0.2157907419880857,"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."}}