{"id":"W3204343880","doi":"10.1016/j.energy.2021.122123","title":"Deep reinforcement learning-based multi-objective control of hybrid power system combined with road recognition under time-varying environment","year":2021,"lang":"en","type":"article","venue":"Energy","topic":"Electric and Hybrid Vehicle Technologies","field":"Engineering","cited_by":64,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body; Fundamental Research Funds for the Central Universities; State Key Laboratory of Mechanical System and Vibration; Natural Science Foundation of Chongqing; National Natural Science Foundation of China","keywords":"Reinforcement learning; Automotive engineering; Fuel efficiency; Computer science; Energy consumption; Artificial neural network; Simulation; Deep learning; Convolutional neural network; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006513542,0.0001651933,0.0002508581,0.00008427573,0.00005706991,0.00001236318,0.0000715353,0.00004930709,0.0001019449],"category_scores_gemma":[0.00001270864,0.0001568837,0.00005424524,0.0001167623,0.00003719254,0.0000522639,0.00001789238,0.0001446148,0.00002241586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001998281,"about_ca_system_score_gemma":0.00002592656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002821118,"about_ca_topic_score_gemma":0.000003782636,"domain_scores_codex":[0.9991542,0.00004309009,0.0002168701,0.0001860849,0.0001711692,0.0002286476],"domain_scores_gemma":[0.9995992,0.00005479713,0.00007406403,0.0001852274,0.00004979021,0.00003693632],"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":[0.00007042619,0.0000401313,0.00006324104,0.00003397513,0.0001668144,0.0000441247,0.00001634588,0.9911448,0.005199552,0.0001469291,0.00002250134,0.003051154],"study_design_scores_gemma":[0.001780782,0.0002999675,0.0001541891,0.00006900462,0.00004193356,0.0000146985,0.00009561795,0.7521259,0.2451066,0.00001494107,0.0001114928,0.0001849451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07868385,0.0006780918,0.9181629,0.00003390523,0.00004942389,0.0001255543,0.000003038323,0.0005948491,0.001668366],"genre_scores_gemma":[0.9988543,0.00003949926,0.0006619668,0.00003350106,0.00000989096,0.00005201955,0.00005887163,0.00003454068,0.0002553429],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9201705,"threshold_uncertainty_score":0.6397532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005430801176628383,"score_gpt":0.1669652928419518,"score_spread":0.1615344916653234,"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."}}