{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007687769,0.0003953603,0.0005352361,0.0001526288,0.00009857135,0.00009967739,0.0001840768,0.0001884557,0.000006859571],"category_scores_gemma":[0.0001500194,0.0004007064,0.0001985646,0.0003520109,0.00001468538,0.0003336284,0.00001293457,0.0003272301,0.00002165645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001000206,"about_ca_system_score_gemma":0.00005196115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001361112,"about_ca_topic_score_gemma":6.79384e-7,"domain_scores_codex":[0.9978147,0.00002094102,0.0008366737,0.0004691656,0.0003049475,0.0005536014],"domain_scores_gemma":[0.998888,0.0003863069,0.00005410756,0.0003554205,0.0001707986,0.0001454345],"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":[0.00001590856,0.000007152951,0.00000850235,0.003947833,0.0001194501,0.000002646068,0.0001553146,0.9868507,0.001467354,0.0008682178,0.00001766152,0.006539209],"study_design_scores_gemma":[0.0009987869,0.00005793791,0.00002478341,0.0007198635,0.00006750657,0.00002821651,0.00007754558,0.9905531,0.000239061,0.00000648901,0.006829832,0.0003968537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003410472,0.0006963544,0.9910651,0.00002843492,0.001498862,0.001739745,0.00008169297,0.004104583,0.0004441197],"genre_scores_gemma":[0.9818677,0.00001434666,0.01653552,0.000004016817,0.0004580567,0.0007739282,0.00006650529,0.0001619373,0.0001179469],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9815267,"threshold_uncertainty_score":0.9998445,"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."}}