{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004287656,0.000384902,0.000372838,0.000590997,0.0003136221,0.0002499965,0.0004529458,0.0003355803,0.0002122256],"category_scores_gemma":[0.0002495137,0.0002548001,0.0001844005,0.0008050067,0.00007751611,0.00003344623,0.0002064233,0.003358629,0.00004820493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009387773,"about_ca_system_score_gemma":0.0003797358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001666308,"about_ca_topic_score_gemma":0.00006035396,"domain_scores_codex":[0.9960192,0.0008773831,0.000440542,0.000604818,0.001373531,0.0006845688],"domain_scores_gemma":[0.9980853,0.0007223057,0.00005647905,0.0008046702,0.000193333,0.0001379601],"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":[0.00007517166,0.00001631704,0.000004141145,0.001414789,0.0000841594,0.00003260051,0.001088387,0.9942018,0.00006612436,0.0006104307,0.0003837091,0.002022394],"study_design_scores_gemma":[0.0002368245,0.0002900693,0.0000489273,0.002701004,0.00002012698,0.000003393558,0.0007592552,0.9928014,0.00004996848,0.00006180078,0.002727743,0.0002994843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006721499,0.001296419,0.9223526,0.001485815,0.0006481967,0.002740159,0.0000441146,0.001277933,0.06343327],"genre_scores_gemma":[0.9907511,0.0001988644,0.005231187,0.0000158998,0.0001345751,0.000738686,0.0001612224,0.0001859362,0.002582452],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9840297,"threshold_uncertainty_score":0.9999904,"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."}}