{"id":"W4385688029","doi":"10.1016/j.engappai.2023.106853","title":"Learn-to-supervise: Causal reinforcement learning for high-level control in industrial processes","year":2023,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Scheduling and Optimization Algorithms","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; Natural Resources Canada","funders":"","keywords":"Reinforcement learning; Computer science; Supervisor; Interpretability; Process (computing); Machine learning; Artificial intelligence; Markov decision process; Supervisory control; Performance indicator; Control (management); Markov process","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":[],"consensus_categories":[],"category_scores_codex":[0.0002968111,0.0001421978,0.0001956342,0.0003918558,0.0000554131,0.00003085488,0.0002034261,0.00009483296,0.00001774525],"category_scores_gemma":[0.0004375291,0.0001704232,0.00003118362,0.001512878,0.00001652469,0.0000687893,0.00002108077,0.0001871673,0.00007176658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005338027,"about_ca_system_score_gemma":0.00004334791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002751113,"about_ca_topic_score_gemma":0.00001040364,"domain_scores_codex":[0.9988878,0.000006545085,0.0004685812,0.000193103,0.0001475966,0.0002963347],"domain_scores_gemma":[0.9993131,0.0002636988,0.00003564515,0.0001696818,0.0001366259,0.00008121803],"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":[0.00001048043,0.00001292239,0.00002691972,0.00008184447,0.00001389426,3.273239e-7,0.0002422673,0.9731631,0.001430134,0.002140596,0.00003406026,0.02284351],"study_design_scores_gemma":[0.00008440902,0.00004249744,0.00003463929,0.00004902208,0.000008428611,3.693403e-7,0.0002062492,0.9715012,0.02697,0.0002048707,0.0007217331,0.0001765992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01129586,0.00003535564,0.9871772,0.00011177,0.0001768211,0.0007040152,0.00001648721,0.0004583263,0.00002414804],"genre_scores_gemma":[0.9702427,0.00002624136,0.02835739,0.000009389648,0.0001853179,0.001015558,0.00005530908,0.00004251822,0.00006562346],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9589468,"threshold_uncertainty_score":0.6949656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04855972969326748,"score_gpt":0.274067345217164,"score_spread":0.2255076155238965,"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."}}