{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001515973,0.0007815746,0.001811281,0.0006067048,0.0005048958,0.0009232189,0.001227689,0.001383505,0.002732415],"category_scores_gemma":[0.004441712,0.0007969873,0.0005780598,0.0004237395,0.00139394,0.000862773,0.001816104,0.001503945,0.000304058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001104816,"about_ca_system_score_gemma":0.001712025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01492176,"about_ca_topic_score_gemma":0.008584142,"domain_scores_codex":[0.999453,0.0002531691,0.00002451276,0.00007486726,0.00009561908,0.00009868173],"domain_scores_gemma":[0.9981133,0.001343915,0.0001575034,0.00009507527,0.0001979771,0.00009225713],"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":[0.00004577026,0.00001847121,0.0001126363,0.00001556831,0.00001389104,0.00001255078,0.00001873373,0.9919083,0.0001844365,0.002646255,0.0001679449,0.004855414],"study_design_scores_gemma":[0.000004879145,0.00001137129,0.00001592121,0.000001905189,0.000001737388,0.00000145873,0.000001308904,0.9991075,0.00003751916,0.0007826756,0.00003219566,0.000001385304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06712688,0.0002476062,0.9257805,0.0002653808,0.0000651538,0.00005941266,0.00005783901,0.0005437036,0.005853531],"genre_scores_gemma":[0.9720997,0.00004661525,0.02549898,0.0000897361,0.00001885252,0.00008856082,0.0000482556,0.00006201662,0.002047143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01492176,"threshold_uncertainty_score":0.02966982,"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."}}