{"id":"W3086953995","doi":"10.1109/access.2020.3022944","title":"Transfer Deep Reinforcement Learning-Enabled Energy Management Strategy for Hybrid Tracked Vehicle","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Electric and Hybrid Vehicle Technologies","field":"Engineering","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Powertrain; Computer science; Energy management; Adaptability; Energy management system; Artificial intelligence; Electric vehicle; Transfer of learning; Artificial neural network; Energy (signal processing); Control engineering; Automotive engineering; Engineering; Power (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":[],"consensus_categories":[],"category_scores_codex":[0.00006099737,0.0002128064,0.0002314437,0.00008325702,0.00009939264,0.0001164564,0.000505633,0.00006274976,0.00006383276],"category_scores_gemma":[0.000006379053,0.0002167417,0.00009139194,0.0002666015,0.00002607073,0.0003783641,0.00002908145,0.0001902417,0.00001650394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005112082,"about_ca_system_score_gemma":0.000009283518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001606468,"about_ca_topic_score_gemma":0.000005951298,"domain_scores_codex":[0.9988344,0.00001079395,0.0002778359,0.000264817,0.0001645948,0.0004475236],"domain_scores_gemma":[0.9996493,0.00003453003,0.00002035839,0.0001686564,0.00003567114,0.00009148186],"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":[0.00007624555,0.00002042064,0.00006461026,0.0002761545,0.0001914817,0.00004177237,0.00005345525,0.859394,0.003152832,0.00428915,0.004438588,0.1280013],"study_design_scores_gemma":[0.001183238,0.0002452538,0.0001085504,0.00001362682,0.00006318314,0.000002502855,0.00005523608,0.7250558,0.2542813,0.0007411002,0.01787781,0.0003723981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2869658,0.0004408288,0.7048981,0.0004216022,0.0001613891,0.0004903097,0.000003311914,0.002088247,0.004530459],"genre_scores_gemma":[0.998327,0.0005360299,0.0001077493,0.0003483077,0.0001063883,0.0002035498,0.00001806751,0.00005325781,0.0002996085],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7113613,"threshold_uncertainty_score":0.8838468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02608168785546356,"score_gpt":0.2418020333026244,"score_spread":0.2157203454471608,"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."}}