{"id":"W4414603383","doi":"10.1109/tte.2025.3615387","title":"Safe Deep Reinforcement Learning for Energy Management of Electrified Vehicles: Optimal Action Filtering and Battery-in-the-Loop Validation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Transportation Electrification","topic":"Advanced Battery Technologies Research","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Reinforcement learning; Powertrain; Benchmark (surveying); Energy management; Metric (unit); Optimal control; Dynamic programming; Minification; Action (physics)","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":[0.001631454,0.0008747489,0.0005548024,0.0003032037,0.0002124222,0.0005515742,0.0009091348,0.0008603623,0.001139738],"category_scores_gemma":[0.005412642,0.0003533143,0.0003012435,0.0001272297,0.0007373473,0.0005636847,0.0009395691,0.001609606,0.0001868235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009124221,"about_ca_system_score_gemma":0.001656259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006898655,"about_ca_topic_score_gemma":0.005324311,"domain_scores_codex":[0.9996481,0.0001236121,0.00001616798,0.00005926826,0.0000892197,0.00006353924],"domain_scores_gemma":[0.9981211,0.001206392,0.0001652278,0.0001184883,0.0002995001,0.00008929478],"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":[0.00005416164,0.00003677942,0.0006666734,0.00003106702,0.00001176704,0.00002850995,0.00002003604,0.9853966,0.0007088226,0.001220136,0.0002243645,0.01160115],"study_design_scores_gemma":[0.000003377959,0.00001164965,0.00003325689,0.000002594723,9.217263e-7,0.000001572628,0.000001514817,0.9992927,0.0002791094,0.0003333641,0.00003917251,7.966917e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1687685,0.0004598806,0.8238687,0.0004998014,0.00007067118,0.00009495809,0.00008629696,0.001789735,0.004361451],"genre_scores_gemma":[0.9731284,0.00005381433,0.02568018,0.00009513838,0.000006824292,0.00006656694,0.00007805007,0.00004241462,0.0008487019],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006898655,"threshold_uncertainty_score":0.013717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01735870452253268,"score_gpt":0.2710587030927269,"score_spread":0.2536999985701942,"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."}}