{"id":"W4283160467","doi":"10.1002/cjce.24508","title":"A survey and comparative evaluation of actor‐critic methods in process control","year":2022,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Robustness (evolution); Computer science; Process (computing); Optimal control; Artificial neural network; Control engineering; Process control; Control (management); Artificial intelligence; Machine learning; Mathematical optimization; Engineering; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.006411848,0.001521905,0.001657221,0.001765331,0.0003705501,0.001916619,0.002052297,0.001611093,0.001888859],"category_scores_gemma":[0.0101569,0.000733524,0.0009327608,0.002059687,0.00106319,0.001223562,0.000956565,0.001619893,0.0003903474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001453714,"about_ca_system_score_gemma":0.001140246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006931486,"about_ca_topic_score_gemma":0.002557232,"domain_scores_codex":[0.9959803,0.001986125,0.0003085486,0.0004589577,0.001160875,0.0001052569],"domain_scores_gemma":[0.9895752,0.007965489,0.0003930608,0.0004785813,0.001435118,0.0001525695],"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":[0.000261274,0.0001622887,0.001177414,0.001815665,0.000328732,0.00004359557,0.00009846492,0.7003798,0.001060996,0.02199874,0.001278683,0.2713943],"study_design_scores_gemma":[0.00002974213,0.0001862042,0.0004523529,0.0002034618,0.00004814778,0.00002700135,0.00002983736,0.9883375,0.001202168,0.004386341,0.005076288,0.00002103168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0206902,0.07607859,0.8801877,0.0009951253,0.0003670237,0.0001772106,0.00009079017,0.0008501045,0.02056328],"genre_scores_gemma":[0.734796,0.05040019,0.2095347,0.0002932117,0.0004446052,0.000267305,0.0002117549,0.0002682479,0.003783913],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006931486,"threshold_uncertainty_score":0.0339095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0722343985281289,"score_gpt":0.3391115488946168,"score_spread":0.2668771503664879,"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."}}