{"id":"W3023365787","doi":"10.1109/tte.2020.2991079","title":"Ensemble Reinforcement Learning-Based Supervisory Control of Hybrid Electric Vehicle for Fuel Economy Improvement","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Transportation Electrification","topic":"Electric Vehicles and Infrastructure","field":"Engineering","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Ensemble learning; Process (computing); Fuel efficiency; Minification; Artificial intelligence; Action (physics); Electric vehicle; State (computer science); Control (management); Engineering; Algorithm; Power (physics); Automotive engineering","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":[0.0005804116,0.0005550317,0.0006282955,0.0002222078,0.0003057465,0.0004425448,0.0006067725,0.0003484094,0.0007920869],"category_scores_gemma":[0.0007833898,0.0002132947,0.0003404123,0.0001667022,0.0002944194,0.0004387517,0.0005408739,0.000549743,0.0001106973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003567638,"about_ca_system_score_gemma":0.000429747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005017126,"about_ca_topic_score_gemma":0.003519169,"domain_scores_codex":[0.9997668,0.00005262133,0.00001225916,0.0000580616,0.000069532,0.0000407951],"domain_scores_gemma":[0.9997074,0.00009973712,0.00005775233,0.00002026752,0.00009340966,0.00002128999],"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":[0.00006923012,0.00004001558,0.000722882,0.00003232908,0.00004344375,0.00005272932,0.00003260471,0.9557067,0.003406963,0.00165598,0.0004239539,0.03781322],"study_design_scores_gemma":[0.00000482626,0.00002773964,0.0001099471,0.000001494307,0.000005018804,0.000005040365,0.00000222176,0.9989623,0.0003635124,0.0003747246,0.0001412059,0.000001987577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1015596,0.0005315036,0.8920907,0.0001757845,0.00009489356,0.00003504067,0.00003000974,0.0004543884,0.005028095],"genre_scores_gemma":[0.9906722,0.00006971704,0.008480118,0.00002346791,0.00001198964,0.00002297332,0.00001852736,0.000007895746,0.0006931169],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005017126,"threshold_uncertainty_score":0.009975851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009735334271715487,"score_gpt":0.1892589650006892,"score_spread":0.1795236307289737,"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."}}