{"id":"W4234587893","doi":"10.22541/au.163252063.31576850/v1","title":"Approximately Optimal Fixed-Structure Controllers Using Neural Networks","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Reinforcement learning; Process (computing); Controller (irrigation); Artificial neural network; Artificial intelligence; Control engineering; Mathematical optimization; Control (management); Control theory (sociology); Engineering; Mathematics","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":[0.00007740635,0.0005816939,0.0008390116,0.0001152928,0.00007733957,0.000288553,0.0003071431,0.0006901349,0.0001412415],"category_scores_gemma":[0.0000286154,0.0005991451,0.0002270339,0.0001629757,0.00003151201,0.0002138693,0.0002638381,0.0009640135,0.000001186224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002720676,"about_ca_system_score_gemma":0.0000407421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003749695,"about_ca_topic_score_gemma":0.00002481207,"domain_scores_codex":[0.9980344,0.00006687446,0.0005925782,0.0005395759,0.000235154,0.0005314721],"domain_scores_gemma":[0.9989093,0.00004952121,0.0001525416,0.0006158712,0.0001422868,0.0001304592],"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":[0.00001550414,0.000004013476,0.00003878088,0.0001457243,0.0001907254,0.00002439763,0.00006133429,0.9977905,0.0007161286,0.00003663847,0.00005828726,0.0009180033],"study_design_scores_gemma":[0.0007069056,0.000005763752,0.00002134433,0.00009158918,0.00008305597,0.00003717508,0.00009381889,0.9982064,0.0001319135,0.00002256418,0.00004017476,0.0005593186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05349416,0.002400493,0.9385051,0.00001775562,0.003014846,0.0007622296,0.00003258429,0.0009282969,0.0008445357],"genre_scores_gemma":[0.9276067,0.0000457863,0.07113245,0.00005298657,0.0006274531,0.00004386293,0.0002642435,0.0001605956,0.0000659045],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8741125,"threshold_uncertainty_score":0.999646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01054279761255795,"score_gpt":0.2172885699502266,"score_spread":0.2067457723376686,"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."}}