{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008698044,0.0007550375,0.0009185396,0.0003224211,0.0003711605,0.000900466,0.001233482,0.0009770069,0.002140188],"category_scores_gemma":[0.002090931,0.0004762663,0.0004904914,0.0002879688,0.0009660766,0.0008830555,0.0009837389,0.001150339,0.0001758736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0013116,"about_ca_system_score_gemma":0.001288062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01075928,"about_ca_topic_score_gemma":0.007863009,"domain_scores_codex":[0.999644,0.0001149263,0.00001181758,0.00009153864,0.00005602522,0.00008171042],"domain_scores_gemma":[0.9990689,0.0004917847,0.0001673701,0.00003938112,0.0001366951,0.00009591781],"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":[0.00002017948,0.00001380358,0.0001997462,0.000009922912,0.0000101188,0.00003840372,0.00001109377,0.9931004,0.0002383926,0.003177436,0.0001330666,0.003047361],"study_design_scores_gemma":[0.000002642882,0.000006159541,0.00001857897,7.663813e-7,0.000001834138,0.000001940261,0.000001815548,0.9992363,0.00003187194,0.0006467592,0.00005024705,9.696952e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06434239,0.0002627526,0.9284044,0.0004603769,0.00007121364,0.00005655447,0.00004402392,0.0002008061,0.006157539],"genre_scores_gemma":[0.9776332,0.0001033678,0.01948798,0.00006650513,0.0000274854,0.0000538947,0.00002748648,0.00002043461,0.002579647],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01075928,"threshold_uncertainty_score":0.02139336,"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."}}