{"id":"W4315750744","doi":"10.1139/cjce-2022-0273","title":"Adaptive traffic signal control using deep Q-learning: case study on optimal implementations","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Traffic control and management","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Implementation; Computer science; Reinforcement learning; Stability (learning theory); Field (mathematics); Intersection (aeronautics); Machine learning; Artificial intelligence; Control (management); Key (lock); Representation (politics); Software engineering; Engineering; Transport engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003068068,0.0001957152,0.000257301,0.0008069137,0.0001314956,0.00007166304,0.000133273,0.00003833145,0.0001064606],"category_scores_gemma":[0.00002473,0.0002122199,0.0001095974,0.0004048339,0.00001118628,0.0001365237,0.000006193856,0.0003558436,0.00001039395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002667725,"about_ca_system_score_gemma":0.0001074266,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002981519,"about_ca_topic_score_gemma":0.04287474,"domain_scores_codex":[0.9988396,0.00002777915,0.0003791586,0.0001111214,0.0001757846,0.0004666125],"domain_scores_gemma":[0.9992337,0.00009941219,0.00005747187,0.00009413093,0.00006551686,0.0004498178],"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":[0.000005740822,0.000009937829,0.00008568553,0.0000114531,0.0002695534,0.008465145,0.001767791,0.985804,0.00009210507,0.00002821805,0.000207873,0.003252545],"study_design_scores_gemma":[0.001536867,0.0003493045,0.001597985,0.00004007254,0.0001342424,0.0008252289,0.008412592,0.9853137,0.000004333505,0.000001037795,0.00155619,0.0002284584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9484232,0.0002184639,0.04995272,0.00003449547,0.0006566867,0.0003164269,0.00001410731,0.0001867857,0.0001970938],"genre_scores_gemma":[0.9995738,0.000003763645,0.0001322145,0.00001075397,0.0002016944,0.00001029548,0.000001535642,0.00005273571,0.0000131526],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05115063,"threshold_uncertainty_score":0.9745903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01722116501756854,"score_gpt":0.2232505682432269,"score_spread":0.2060294032256584,"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."}}