{"id":"W3132515107","doi":"10.1109/vtc2020-fall49728.2020.9348674","title":"Average Reward Reinforcement Learning for Optimal On-route Charging of Electric Buses","year":2020,"lang":"en","type":"article","venue":"","topic":"Electric Vehicles and Infrastructure","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Schedule; Reinforcement learning; Markov decision process; Computer science; Battery (electricity); Grid; Process (computing); Markov process; Operations research; Automotive engineering; Engineering; Power (physics); Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000485149,0.0001255382,0.000174089,0.00005731604,0.00004430114,0.00001556513,0.0001027105,0.00005218878,0.0001333616],"category_scores_gemma":[0.00003698943,0.0001135514,0.00007299408,0.0002272115,0.000004364259,0.00006735498,0.00001359766,0.0001866237,0.000009180892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000370488,"about_ca_system_score_gemma":0.00001286892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003658747,"about_ca_topic_score_gemma":1.335483e-7,"domain_scores_codex":[0.9992938,0.000005710279,0.0002044689,0.0001250079,0.0001188224,0.0002521608],"domain_scores_gemma":[0.9997534,0.00004042423,0.00003492023,0.00007490207,0.00002994901,0.00006637748],"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":[0.00003009366,0.000002268646,0.0001659509,0.00009123766,0.00004187292,9.6709e-7,0.0002340792,0.9623647,0.02773752,0.001147507,0.002008605,0.006175179],"study_design_scores_gemma":[0.0003865281,0.000417318,0.0001742447,0.00001253105,0.000009635385,0.000001240596,0.00002751277,0.8414076,0.1457996,0.00002787304,0.01158797,0.0001479914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4531597,0.0002723412,0.5306476,0.0002978419,0.0001030504,0.0004750257,0.000003121197,0.0005790083,0.01446225],"genre_scores_gemma":[0.9976114,0.00006537538,0.001688355,0.0002604667,0.000128484,0.00001046624,0.00001308456,0.00002941311,0.0001929565],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5444517,"threshold_uncertainty_score":0.4630491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01013950576085302,"score_gpt":0.2032736201097587,"score_spread":0.1931341143489057,"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."}}