{"id":"W4365460520","doi":"10.48550/arxiv.2304.05509","title":"Control invariant set enhanced reinforcement learning for process control: improved sampling efficiency and guaranteed stability","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Backup; Computer science; Stability (learning theory); Sampling (signal processing); Process (computing); Invariant (physics); State (computer science); Artificial intelligence; Control theory (sociology); Control (management); Machine learning; Mathematical optimization; Algorithm; Mathematics; Detector","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":[0.001293286,0.0006041229,0.0007154588,0.0002682042,0.0002136309,0.0005577038,0.0008001541,0.0004877583,0.001519729],"category_scores_gemma":[0.003832784,0.0002466567,0.0003224233,0.000204292,0.0007874212,0.0005979095,0.0007208113,0.001108673,0.0002021017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005191687,"about_ca_system_score_gemma":0.0008290633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003011235,"about_ca_topic_score_gemma":0.002069596,"domain_scores_codex":[0.9995021,0.0001595047,0.00002280453,0.00009279246,0.0001584646,0.00006435968],"domain_scores_gemma":[0.9985184,0.0008993047,0.0001718485,0.0001394593,0.0002209187,0.00005004687],"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":[0.0001452644,0.00007575476,0.0005732818,0.00006350237,0.0000251033,0.00006435945,0.00004387917,0.9388589,0.004976664,0.006333943,0.0004193214,0.04842005],"study_design_scores_gemma":[0.000006820246,0.00003114544,0.00003776153,0.000001782017,0.000001841875,0.000004557458,8.833831e-7,0.9985816,0.0006628195,0.0005770498,0.00009194959,0.000001830388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0339355,0.0001827001,0.9630396,0.0001120817,0.00003161667,0.00003604502,0.00001551561,0.0004755746,0.002171403],"genre_scores_gemma":[0.946744,0.00007108075,0.05192663,0.00005966917,0.00001986922,0.00005299671,0.00002914342,0.00004432409,0.001052299],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003011235,"threshold_uncertainty_score":0.006839633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05053102258716711,"score_gpt":0.2040948357973252,"score_spread":0.1535638132101581,"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."}}