{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001117011,0.0007275507,0.001125711,0.0003448318,0.0002820827,0.0005153008,0.0008087499,0.0007127788,0.002114153],"category_scores_gemma":[0.003281203,0.0004034365,0.0003621153,0.0002404548,0.0006367356,0.0004973208,0.0006562055,0.001108268,0.0001779391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000945966,"about_ca_system_score_gemma":0.001565735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01469716,"about_ca_topic_score_gemma":0.009457002,"domain_scores_codex":[0.9995389,0.0001766325,0.00001858979,0.00007764663,0.00007103375,0.0001172918],"domain_scores_gemma":[0.9985036,0.0009658911,0.0001663805,0.00003968698,0.0002245883,0.00009990454],"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":[0.00006460878,0.000045722,0.0003260763,0.00002133516,0.00001164234,0.00002623551,0.00001685876,0.9904184,0.0002594682,0.001099363,0.0002618596,0.007448439],"study_design_scores_gemma":[0.000006042222,0.00001427831,0.00003999186,0.000001066444,0.000001957892,0.000001590421,0.000001746239,0.9995635,0.00004411914,0.0002951649,0.00002941478,0.000001092949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2279816,0.0008883633,0.7612727,0.0005770398,0.0001313632,0.0001209615,0.00007899744,0.001121864,0.007827277],"genre_scores_gemma":[0.9874068,0.00007874304,0.01116943,0.00006171135,0.00001426349,0.00003996368,0.0000372489,0.00002171553,0.001170288],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01469716,"threshold_uncertainty_score":0.02922326,"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."}}