{"id":"W4401880651","doi":"10.1109/icps59941.2024.10640031","title":"Deep reinforcement learning-based model predictive control of uncertain linear systems","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Model predictive control; Computer science; Artificial intelligence; Control (management); Machine learning; Control theory (sociology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008104425,0.0007534598,0.0008582155,0.0002608337,0.000274788,0.0006787271,0.0008044438,0.0006339134,0.001282117],"category_scores_gemma":[0.001681057,0.0003695258,0.000348581,0.0003063853,0.0006818641,0.0005366699,0.0009836218,0.001239073,0.0001939552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007234928,"about_ca_system_score_gemma":0.001115336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0097895,"about_ca_topic_score_gemma":0.006740803,"domain_scores_codex":[0.9996967,0.00008275139,0.00001481694,0.0000534848,0.00009805775,0.0000541734],"domain_scores_gemma":[0.999464,0.0002722081,0.00008687319,0.00003562352,0.0001137843,0.00002758888],"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":[0.00001951801,0.000009441264,0.000105826,0.00002393153,0.000009612577,0.00001984035,0.00001371497,0.9854608,0.0004474207,0.002539712,0.0002371537,0.01111306],"study_design_scores_gemma":[0.000001659168,0.00000548042,0.00001176344,0.000001199069,8.268351e-7,0.000001156733,5.448316e-7,0.9994142,0.00006627215,0.0004271727,0.00006902316,7.40701e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01580686,0.0004943688,0.9800208,0.0002353805,0.00006133175,0.00002559425,0.00003540633,0.0004061155,0.002914114],"genre_scores_gemma":[0.9635531,0.0002486563,0.03366949,0.00009244657,0.00004159338,0.00007852164,0.00007021257,0.00003607752,0.002209908],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0097895,"threshold_uncertainty_score":0.01946503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006983298468713695,"score_gpt":0.2160294723540002,"score_spread":0.2090461738852865,"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."}}