{"id":"W4399385035","doi":"10.21203/rs.3.rs-4449743/v1","title":"A train trajectory optimization method based on the safety reinforcement learning with a relaxed dynamic reward","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Railway Systems and Energy Efficiency","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"SR Research (Canada)","funders":"","keywords":"Reinforcement learning; Trajectory; Computer science; Reinforcement; Artificial intelligence; Psychology; Social psychology; Physics","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":[0.0006872579,0.0006337702,0.000860895,0.0004100148,0.0004031782,0.0005536273,0.0008769659,0.000743967,0.00255191],"category_scores_gemma":[0.001298522,0.0003462858,0.0005840946,0.0004339464,0.000521909,0.0007071667,0.001012848,0.001184211,0.0003355531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005538519,"about_ca_system_score_gemma":0.001648079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006456347,"about_ca_topic_score_gemma":0.003680823,"domain_scores_codex":[0.9996971,0.00007637433,0.00001741831,0.00007152971,0.00009219112,0.00004537198],"domain_scores_gemma":[0.9995931,0.0001742237,0.00005406973,0.00003126962,0.000106018,0.00004126184],"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":[0.00005724116,0.00003989809,0.0004634967,0.00005351076,0.00002472988,0.00005219343,0.00004473316,0.9346856,0.002191932,0.008929281,0.0008689656,0.05258836],"study_design_scores_gemma":[0.000006059772,0.00001492077,0.00002801324,0.000001721272,0.000002358581,0.000005445051,0.000001837923,0.99883,0.0002071626,0.0006671559,0.0002333026,0.000002004276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006868121,0.00007228711,0.991376,0.00008323379,0.00002436174,0.00003448936,0.00001647024,0.00018659,0.001338465],"genre_scores_gemma":[0.6757697,0.0002151617,0.3164678,0.0001451294,0.00006164822,0.0003034935,0.0001676804,0.0001316113,0.006737824],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006456347,"threshold_uncertainty_score":0.01283753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02408025858117876,"score_gpt":0.3124727896332973,"score_spread":0.2883925310521185,"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."}}