{"id":"W4392654438","doi":"10.1016/j.jfranklin.2024.106717","title":"Asynchronous deep reinforcement learning with gradient sharing for State of Charge balancing of multiple batteries in cyber–physical electric vehicles","year":2024,"lang":"en","type":"article","venue":"Journal of the Franklin Institute","topic":"Advanced Battery Technologies Research","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Asynchronous communication; Reinforcement learning; Cyber-physical system; Asynchronous learning; Computer science; Reinforcement; Charge (physics); State (computer science); Electrical engineering; Engineering; Computer network; Artificial intelligence; Psychology; Physics; Synchronous learning; Mathematics education; Cooperative learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002798786,0.0001348361,0.0003188375,0.0003111961,0.00004591618,0.00002213866,0.0003775139,0.00003692423,0.00000259195],"category_scores_gemma":[0.0001451759,0.00009143932,0.0001102086,0.0004361168,0.00008727408,0.0003069463,0.00009147266,0.0005536186,9.180155e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002151796,"about_ca_system_score_gemma":0.00004886878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001190605,"about_ca_topic_score_gemma":0.0000311453,"domain_scores_codex":[0.9988462,0.00001285074,0.0004669224,0.0001094551,0.0002846128,0.0002799494],"domain_scores_gemma":[0.9994437,0.0001390891,0.0001436128,0.0001679953,0.00007627729,0.00002938306],"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":[0.00008891794,0.00002373229,0.003700483,0.0004581112,0.0001269179,0.0000181723,0.0006575795,0.8972113,0.07709309,0.0001599249,0.00001035317,0.02045145],"study_design_scores_gemma":[0.0007294492,0.0003937869,0.002375567,0.0009282527,0.00002868653,0.00003397401,0.00007827319,0.7274587,0.266547,0.0005731945,0.000713622,0.0001394882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8993122,0.0006508752,0.0994098,0.00006053974,0.0002341402,0.000253072,0.000002366263,0.00003958576,0.00003745389],"genre_scores_gemma":[0.998226,0.0001873704,0.001460901,0.000004051405,0.00005418555,0.00002125109,8.884417e-7,0.00002610822,0.00001921697],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1894539,"threshold_uncertainty_score":0.3728787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01045938892361378,"score_gpt":0.2445835587805655,"score_spread":0.2341241698569517,"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."}}