{"id":"W4413967003","doi":"10.1109/access.2025.3605874","title":"Implementation of Deep Reinforcement Learning for Model-free Switching And Control of a 23-level Single DC Source Hybrid Packed U-Cell (HPUC)","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Silicon Carbide Semiconductor Technologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hydro-Québec; École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Reinforcement learning; Computer science; Control (management); Artificial intelligence","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":[0.0003781763,0.0004903818,0.0004132176,0.0001439839,0.0002132004,0.000434128,0.0008505122,0.0004699505,0.00197904],"category_scores_gemma":[0.0005922082,0.0001944138,0.0002681674,0.0001069851,0.0003577653,0.0003171461,0.0005407133,0.0007509137,0.0002909928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004807523,"about_ca_system_score_gemma":0.0007683992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005283035,"about_ca_topic_score_gemma":0.006317827,"domain_scores_codex":[0.9998617,0.00002392985,0.000007241792,0.00003317816,0.0000459474,0.00002796078],"domain_scores_gemma":[0.9998165,0.00006225508,0.00002867389,0.00001973748,0.00005462556,0.00001820019],"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":[0.00008703158,0.00009059533,0.0007881841,0.00007705785,0.00003727188,0.00009899965,0.00006390965,0.8788551,0.0106401,0.004485681,0.001032148,0.103744],"study_design_scores_gemma":[0.000003769634,0.00002776958,0.0000380423,0.000002033835,0.000002301179,0.000006985525,0.00000175808,0.9985414,0.0008794075,0.0002625707,0.0002321324,0.000001901395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03298681,0.0001719766,0.9605018,0.0001373304,0.0000678038,0.00005771928,0.00002778319,0.0009360152,0.005112716],"genre_scores_gemma":[0.9254969,0.00005439563,0.07220699,0.00009000686,0.00001412259,0.00009204899,0.00003932892,0.00002921409,0.001976945],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005283035,"threshold_uncertainty_score":0.01050454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02568922063259413,"score_gpt":0.2804805542636314,"score_spread":0.2547913336310373,"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."}}