{"id":"W4414955876","doi":"10.1109/tste.2025.3619196","title":"Coordination of Power and Transportation Networks With Integrated Electricity-Hydrogen Stations: A Reinforcement Learning Approach Considering Delayed Reward","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Sustainable Energy","topic":"Electric Vehicles and Infrastructure","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Queen's University; National Natural Science Foundation of China; Queen's University Belfast","keywords":"Reinforcement learning; Markov decision process; Dynamic pricing; Markov process; Revenue; Q-learning; Traffic congestion; Process (computing); Vehicle dynamics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009099019,0.0001798664,0.0002035313,0.000379823,0.0001748309,0.0000301372,0.00005428659,0.0001172111,0.0000151675],"category_scores_gemma":[0.000003404754,0.0001721445,0.00004056906,0.001037823,0.00003559089,0.0001942749,4.08992e-7,0.0002854146,7.204662e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001768078,"about_ca_system_score_gemma":0.00008069866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004117017,"about_ca_topic_score_gemma":0.00006616737,"domain_scores_codex":[0.9990841,0.00002986636,0.0002897549,0.0001814998,0.0001286288,0.0002861971],"domain_scores_gemma":[0.999529,0.00005455162,0.00005652828,0.0001074296,0.0002076186,0.0000448755],"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":[0.0001058517,0.00002265003,0.00002347257,0.00008169826,0.0001849291,0.000003799602,0.0002389236,0.9893587,0.001012248,0.003077185,0.00006016707,0.005830352],"study_design_scores_gemma":[0.0009180823,0.0003681345,0.00008072643,0.00005193909,0.0001125686,0.00000620301,0.001831782,0.9638384,0.03077097,0.0002550714,0.001533662,0.0002324895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1136905,0.0002192395,0.8847312,0.00001800385,0.00002890417,0.000168109,0.000002088287,0.0001411461,0.001000812],"genre_scores_gemma":[0.9976099,0.0001930168,0.0008566236,0.0000319439,0.000004581747,0.00007578066,0.00003040146,0.00002593131,0.001171843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8839194,"threshold_uncertainty_score":0.7019849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.002562765029531205,"score_gpt":0.1781340399843105,"score_spread":0.1755712749547793,"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."}}