{"id":"W3009193590","doi":"10.1016/j.energy.2020.117297","title":"Rule-interposing deep reinforcement learning based energy management strategy for power-split hybrid electric vehicle","year":2020,"lang":"en","type":"article","venue":"Energy","topic":"Electric Vehicles and Infrastructure","field":"Engineering","cited_by":348,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Energy management; Computer science; Artificial intelligence; Electric vehicle; Process (computing); Deep learning; Battery (electricity); Brake; Industrial engineering; Mathematical optimization; Automotive engineering; Energy (signal processing); Power (physics); Engineering; Mathematics","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":[0.00005666829,0.0002744181,0.000237745,0.0001160239,0.0001293125,0.00008911329,0.0002326787,0.00007362063,0.0001690588],"category_scores_gemma":[0.000008256997,0.0002886354,0.000133938,0.0003349483,0.000009651484,0.0001175038,0.00003748836,0.0001785719,0.000006786383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001368791,"about_ca_system_score_gemma":0.00001940482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000281443,"about_ca_topic_score_gemma":0.000003266234,"domain_scores_codex":[0.9985681,0.00002389343,0.0003282767,0.0003113202,0.0002074758,0.000560961],"domain_scores_gemma":[0.9995186,0.0000382978,0.00005973532,0.0001719644,0.00003921863,0.0001722045],"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":[0.00004627288,0.000007773201,0.00001303339,0.00006347291,0.00009710233,0.00001849785,0.00003368531,0.8884351,0.01131694,0.009217978,0.001380068,0.08937014],"study_design_scores_gemma":[0.0006121174,0.0003134503,0.00006039696,0.00001840796,0.00002814962,0.000003302102,0.00002409835,0.8656367,0.06862732,0.0002901564,0.06408661,0.0002993138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02035418,0.001165073,0.9642735,0.0001826685,0.0001776149,0.0001361676,0.000002051838,0.0005740168,0.01313471],"genre_scores_gemma":[0.9971693,0.000107569,0.0009952302,0.0009781761,0.0001875683,0.00005886736,0.00006003859,0.00008188713,0.0003614109],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.976815,"threshold_uncertainty_score":0.9999566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005796716055064546,"score_gpt":0.189519297091785,"score_spread":0.1837225810367205,"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."}}