{"id":"W3087814763","doi":"10.1109/tvt.2020.3026004","title":"Autonomous PEV Charging Scheduling Using Dyna-Q Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Electric Vehicles and Infrastructure","field":"Engineering","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Toronto Metropolitan University; Bell (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Markov decision process; Q-learning; Computer science; Scheduling (production processes); Markov process; Artificial intelligence; Artificial neural network; Bellman equation; Markov chain; State space; Mathematical optimization; Simulation; Machine learning; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00005706333,0.0002540258,0.0002643929,0.000314939,0.0002604561,0.00003193784,0.0002124722,0.0003348756,0.0001179345],"category_scores_gemma":[0.000006497457,0.0002777563,0.0001121106,0.0007884254,0.00004947309,0.0001209989,0.000002751182,0.001189461,0.00005766608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001824313,"about_ca_system_score_gemma":0.00003020157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006771084,"about_ca_topic_score_gemma":0.000001386294,"domain_scores_codex":[0.9987903,0.00001603482,0.000295671,0.000293858,0.0001580234,0.0004460615],"domain_scores_gemma":[0.9995893,0.00001450562,0.00004664008,0.0002077417,0.00003967809,0.0001021415],"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":[0.000005800854,0.000006817143,0.00001559373,0.00003502851,0.00007423465,0.00001887378,0.0001107991,0.8884543,0.08511645,0.0001420799,0.000005532633,0.02601453],"study_design_scores_gemma":[0.0002942763,0.0001275815,0.00000371595,0.00003000179,0.00003963397,0.00004476024,0.0001259311,0.824519,0.17277,0.00005513246,0.001750706,0.000239246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2634232,0.0002144177,0.7339865,0.0004511247,0.000172459,0.0001492589,0.000001525126,0.001442403,0.0001591128],"genre_scores_gemma":[0.9929286,0.00008667029,0.006625181,0.0001721457,0.00007423485,0.00002021231,0.000002471345,0.0000663942,0.00002411902],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7295054,"threshold_uncertainty_score":0.9999675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009543680068389623,"score_gpt":0.206070726635678,"score_spread":0.1965270465672883,"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."}}