{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006618153,0.000681324,0.0009638682,0.0002746062,0.0003903852,0.0006125678,0.001207411,0.0006648451,0.001683265],"category_scores_gemma":[0.001468574,0.0004548084,0.0003698891,0.0002597737,0.0005306951,0.0006318953,0.0007523689,0.0009318086,0.0001971241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007073174,"about_ca_system_score_gemma":0.00159665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009340143,"about_ca_topic_score_gemma":0.006920676,"domain_scores_codex":[0.9997194,0.00006868284,0.00001446997,0.00006893561,0.00006453392,0.00006393689],"domain_scores_gemma":[0.9993888,0.0003142187,0.00009275594,0.00003233265,0.0001069371,0.00006477668],"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":[0.00005715738,0.00005700039,0.0006141418,0.00003112184,0.00002132724,0.00005759007,0.00003141389,0.972638,0.001098127,0.002380109,0.0005880443,0.02242596],"study_design_scores_gemma":[0.000006806604,0.0000124023,0.00004018389,0.000001014485,0.000002132534,0.000004492807,0.000002506337,0.9992061,0.0001086355,0.0004971481,0.0001170198,0.000001493933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0524488,0.0002338583,0.9425352,0.0002972613,0.00008476544,0.00007494047,0.00004581229,0.0007253834,0.003553871],"genre_scores_gemma":[0.9711675,0.00005643932,0.02693079,0.00008200431,0.00001632082,0.00006475369,0.00003968602,0.00002734042,0.001615084],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009340143,"threshold_uncertainty_score":0.01857156,"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."}}