{"id":"W4403412837","doi":"10.1002/oca.3216","title":"Mixed‐Integer Optimal Control via Reinforcement Learning: A Case Study on Hybrid Electric Vehicle Energy Management","year":2024,"lang":"en","type":"article","venue":"Optimal Control Applications and Methods","topic":"Electric Vehicles and Infrastructure","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Electric vehicle; Energy management; Integer programming; Integer (computer science); Control (management); Mathematical optimization; Reinforcement; Computer science; Energy (signal processing); Engineering; Artificial intelligence; Mathematics; Structural engineering; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004425882,0.0003238595,0.0003494674,0.0002534798,0.0002349185,0.0001712205,0.00014558,0.00007842071,0.00004461589],"category_scores_gemma":[0.000006378133,0.0002876705,0.0001126577,0.0004446637,0.00002501692,0.0001055934,0.00003172785,0.0004299238,0.00001342947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001075129,"about_ca_system_score_gemma":0.00001644433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004237883,"about_ca_topic_score_gemma":0.00000149265,"domain_scores_codex":[0.9983778,0.0001455967,0.0003910253,0.0004659022,0.0001785234,0.0004411737],"domain_scores_gemma":[0.9991921,0.000230368,0.00004360088,0.0003167501,0.00005346036,0.0001637339],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006773722,0.00007608385,0.00001907112,0.00005270975,0.0005591482,0.0002806446,0.00009663113,0.352522,0.00621133,0.005349841,0.0003350143,0.6344298],"study_design_scores_gemma":[0.00135996,0.0005644644,0.00009141023,0.00001128009,0.0002845569,0.0003909499,0.0002036568,0.940416,0.001291683,0.0001140437,0.054964,0.0003080188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02600878,0.002402003,0.9683113,0.00007168674,0.00008704574,0.0009895276,0.000005902883,0.0003751774,0.00174856],"genre_scores_gemma":[0.9814028,0.0001898248,0.01617744,0.0001228324,0.0001527463,0.001398764,0.000008234434,0.0000628031,0.0004845768],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.955394,"threshold_uncertainty_score":0.9999576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007282110080568093,"score_gpt":0.2674272158032656,"score_spread":0.2601451057226975,"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."}}