{"id":"W4249623644","doi":"10.32920/ryerson.14661024","title":"Autonomous PEV Charging Scheduling Using Deep-Q Network and Dyna-Q Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Electric Vehicles and Infrastructure","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Q-learning; Markov decision process; Computer science; Scheduling (production processes); Mathematical optimization; Set (abstract data type); Markov chain; Artificial intelligence; State space; Artificial neural network; Markov process; Machine learning; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071923,0.0006260701,0.0008289291,0.0002641444,0.0003723259,0.0006606118,0.001250881,0.0007838928,0.001579768],"category_scores_gemma":[0.001392185,0.0004981722,0.0004238276,0.0002788842,0.0005950508,0.0007245661,0.0008533664,0.001091429,0.0001878327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001063322,"about_ca_system_score_gemma":0.001561936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01561779,"about_ca_topic_score_gemma":0.01143813,"domain_scores_codex":[0.9997725,0.00006065487,0.00001139313,0.00005652717,0.00004211115,0.00005684125],"domain_scores_gemma":[0.9994517,0.0002800255,0.00006923256,0.0000312446,0.0001113892,0.00005634953],"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":[0.00003762934,0.00004554062,0.0004502974,0.00001887994,0.00001651305,0.00003845331,0.00002138752,0.977007,0.000542085,0.00202823,0.0004127231,0.0193812],"study_design_scores_gemma":[0.000002598473,0.000005659831,0.00001925002,5.891428e-7,9.298973e-7,0.000001546823,0.000001320809,0.9994981,0.00004782754,0.0003738759,0.00004743001,8.1076e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06659934,0.0003779906,0.9267761,0.0004796982,0.0001055174,0.00006762033,0.00006107426,0.000762027,0.004770608],"genre_scores_gemma":[0.9583083,0.00008751178,0.03910496,0.0001239407,0.0000230711,0.00007253971,0.00006087526,0.00002969968,0.002189164],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01561779,"threshold_uncertainty_score":0.03105378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008745657377777613,"score_gpt":0.2106575166761389,"score_spread":0.2019118592983613,"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."}}