{"id":"W4404409632","doi":"10.1016/j.ress.2024.110639","title":"A novel sim2real reinforcement learning algorithm for process control","year":2024,"lang":"en","type":"article","venue":"Reliability Engineering & System Safety","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"China Scholarship Council; National Natural Science Foundation of China; Central South University; University of Alberta","keywords":"Reinforcement learning; Process (computing); Computer science; Control (management); Algorithm; Reinforcement; Process control; Artificial intelligence; Machine learning; Engineering; Programming language; Structural engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000847122,0.00058762,0.0008029306,0.0003655085,0.0004130139,0.0005753181,0.001680963,0.0008813147,0.004946171],"category_scores_gemma":[0.001261455,0.0003020131,0.0003546726,0.0003149201,0.0004804605,0.0005684307,0.001147245,0.0009131561,0.0008289124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000618502,"about_ca_system_score_gemma":0.001127053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004544015,"about_ca_topic_score_gemma":0.004583703,"domain_scores_codex":[0.9996009,0.00009517467,0.00001596732,0.0000840864,0.0001545434,0.00004929993],"domain_scores_gemma":[0.9995847,0.0001431951,0.00003539294,0.00005202117,0.0001465333,0.00003808851],"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":[0.0003797642,0.0001694972,0.0006797991,0.00009739219,0.0000571434,0.00007312447,0.00004613231,0.7096761,0.006117335,0.01282519,0.003626491,0.266252],"study_design_scores_gemma":[0.00001187343,0.0000248451,0.00002524104,0.000001048488,0.000001780984,0.000007278154,9.100621e-7,0.9987771,0.0003726461,0.0004487014,0.0003268529,0.00000178767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008503626,0.0001239938,0.9876919,0.00008075771,0.00008394446,0.00003561615,0.00002399803,0.0007843603,0.002671699],"genre_scores_gemma":[0.5355098,0.0001163072,0.4565744,0.0002342082,0.0000962534,0.0001809482,0.0001449553,0.0001684226,0.006974635],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004946171,"threshold_uncertainty_score":0.01654661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003341485487987499,"score_gpt":0.2029398712035784,"score_spread":0.1995983857155909,"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."}}