{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001631199,0.0005788093,0.0005896588,0.0002865441,0.0003558385,0.0005710157,0.001055968,0.001008083,0.002467216],"category_scores_gemma":[0.005714706,0.0003842452,0.0002721686,0.000221575,0.0008765202,0.0007854125,0.001081554,0.001886649,0.0002209204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006414519,"about_ca_system_score_gemma":0.001322905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00650472,"about_ca_topic_score_gemma":0.007485118,"domain_scores_codex":[0.9996138,0.000141216,0.00001866622,0.00007735399,0.0000996312,0.00004930555],"domain_scores_gemma":[0.9982017,0.001248561,0.000127724,0.0001226725,0.0002076888,0.00009164766],"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":[0.0002885583,0.0001530258,0.0005655529,0.000099611,0.00002914902,0.00005334183,0.00007268838,0.8742136,0.002159522,0.01013282,0.001381121,0.1108509],"study_design_scores_gemma":[0.00001049578,0.00002372282,0.00003686111,0.000001817363,0.000002041694,0.000003189833,0.0000014211,0.9978257,0.0003752903,0.001623733,0.00009368733,0.000001945205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02879928,0.0002349681,0.9679404,0.0002764261,0.00008519344,0.00006104793,0.00003324529,0.001161629,0.001407849],"genre_scores_gemma":[0.9282772,0.00009364083,0.07004724,0.0001081323,0.00003691635,0.00007983123,0.00003700733,0.0000710766,0.001248938],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00650472,"threshold_uncertainty_score":0.01293373,"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."}}