{"id":"W4321225876","doi":"10.1177/09596518231153445","title":"Safe deep reinforcement learning in diesel engine emission control","year":2023,"lang":"en","type":"article","venue":"Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Reinforcement; Reinforcement learning; Diesel engine; Automotive engineering; Control (management); Diesel fuel; Computer science; Environmental science; Artificial intelligence; Engineering; 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":[],"consensus_categories":[],"category_scores_codex":[0.00104708,0.000245719,0.0007267002,0.0004092269,0.00004623004,0.00002381226,0.0002394278,0.0001528008,0.000001556424],"category_scores_gemma":[0.0005848755,0.0001959366,0.0001516437,0.00055215,0.00002791276,0.0003765869,0.00003174907,0.0004218664,5.857499e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001466438,"about_ca_system_score_gemma":0.0000264866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005429809,"about_ca_topic_score_gemma":2.994156e-7,"domain_scores_codex":[0.9978391,0.00001205151,0.001261017,0.0001293986,0.000449129,0.0003092891],"domain_scores_gemma":[0.9989259,0.0001286802,0.000434041,0.00008555366,0.0003033669,0.0001224538],"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":[0.00005943386,0.000008687095,0.0001221669,0.0005371908,0.0001181175,0.000002092507,0.0001001918,0.9292492,0.06614657,0.003268031,0.00001990953,0.0003683866],"study_design_scores_gemma":[0.002803321,0.0001163027,0.0001496146,0.001318415,0.00006556737,0.00003943058,0.000204829,0.9910108,0.003370237,0.000022137,0.0007289071,0.000170466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1317485,0.003525218,0.8606863,0.0001790067,0.002375662,0.000993069,0.000006368598,0.000243294,0.0002426276],"genre_scores_gemma":[0.9991458,0.000349235,0.00024876,0.000003904637,0.0001649323,0.00002635389,7.814218e-7,0.00003258599,0.00002766975],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8673973,"threshold_uncertainty_score":0.7990061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005549480386290023,"score_gpt":0.1875978016516738,"score_spread":0.1820483212653838,"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."}}