{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003303711,0.00005264439,0.0001554729,0.0001223802,0.00003435402,0.00002755342,0.0003801963,0.00001475038,0.0000093139],"category_scores_gemma":[0.0006596919,0.00004503988,0.00001955643,0.000260423,0.00002775367,0.00009719244,0.00002227787,0.0003040078,5.673254e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002012505,"about_ca_system_score_gemma":0.0005013688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003638491,"about_ca_topic_score_gemma":0.00008099902,"domain_scores_codex":[0.9990571,0.0002364534,0.0002369867,0.00005325618,0.0002897984,0.0001264431],"domain_scores_gemma":[0.9991065,0.0004259145,0.0001072821,0.0000873677,0.0001732395,0.00009970826],"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":[0.00000253933,0.000001765577,0.0007209767,0.000007133974,0.00001354701,0.000001708789,0.001108382,0.9940177,0.003501439,0.0003049285,0.000005152589,0.0003146946],"study_design_scores_gemma":[0.0003631976,0.00002943232,0.003169186,0.00001640462,0.000009297667,0.00002609611,0.00003030949,0.9926326,0.003568233,0.00009077345,0.00001704187,0.00004746335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6657621,0.0006111242,0.332931,0.000295308,0.0001854639,0.0001462147,0.000002334458,0.000004221896,0.00006220013],"genre_scores_gemma":[0.9970629,2.255094e-7,0.002896517,0.00002369654,0.000008989037,0.000003384109,3.647304e-7,0.00000277434,0.00000115712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3313008,"threshold_uncertainty_score":0.1836673,"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."}}