{"id":"W4412465510","doi":"10.1016/j.cie.2025.111372","title":"IRS-guided policy search in model based reinforcement learning for virtually coupled train sets control","year":2025,"lang":"en","type":"article","venue":"Computers & Industrial Engineering","topic":"Railway Systems and Energy Efficiency","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Reinforcement learning; Reinforcement; Control (management); Computer science; Artificial intelligence; Engineering; Operations research; Structural engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005975455,0.0003089232,0.0004499808,0.0007273,0.00007653941,0.00008619584,0.0002953828,0.0002554395,0.000003256643],"category_scores_gemma":[0.0001809713,0.0003519425,0.0001336555,0.0006432721,0.00001645953,0.0001075893,0.00003463273,0.0004690501,0.000001810799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005214817,"about_ca_system_score_gemma":0.0002740134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001262407,"about_ca_topic_score_gemma":0.000005103127,"domain_scores_codex":[0.9982174,0.00002712541,0.000607786,0.0002861237,0.0002108415,0.0006507349],"domain_scores_gemma":[0.999279,0.0002868274,0.000034545,0.0002263505,0.00005180131,0.0001215324],"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":[0.00002896626,0.00001256987,0.00002507782,0.00009116292,0.00005302727,0.000003560281,0.0001481426,0.9890306,0.003600041,0.001773597,0.0003690514,0.004864175],"study_design_scores_gemma":[0.004689997,0.00006232126,0.00003879767,0.0002826162,0.00001177847,0.000001023625,0.00002268632,0.9926896,0.0005006566,0.000007022131,0.001395629,0.000297854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06686678,0.00006011433,0.9305629,0.0001632002,0.0009018416,0.0006454516,0.000004357925,0.0004117934,0.000383637],"genre_scores_gemma":[0.9976488,0.000004157565,0.001614749,0.0000751862,0.0003039151,0.0001257148,0.00002346826,0.00005426383,0.0001497751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.930782,"threshold_uncertainty_score":0.9998932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0248354182317124,"score_gpt":0.2481351192590191,"score_spread":0.2232997010273067,"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."}}