{"id":"W2904906709","doi":"10.1109/itsc.2018.8569549","title":"Deep Learning vs. Discrete Reinforcement Learning for Adaptive Traffic Signal Control","year":2018,"lang":"en","type":"article","venue":"","topic":"Traffic control and management","field":"Engineering","cited_by":71,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Intersection (aeronautics); Queue; Deep learning; Population; Controller (irrigation); Adaptive control; SIGNAL (programming language); Artificial intelligence; Control (management); Real-time computing; Engineering; Transport engineering; Computer network","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":[0.0008772446,0.0006581991,0.0005821044,0.0002025773,0.0001703493,0.0006421464,0.0007104148,0.0008547161,0.001522358],"category_scores_gemma":[0.002678405,0.0002352852,0.0002827882,0.00025732,0.0007727466,0.0007217233,0.0006225781,0.001596655,0.0001722308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009128699,"about_ca_system_score_gemma":0.0009046269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006007318,"about_ca_topic_score_gemma":0.003580651,"domain_scores_codex":[0.9997182,0.00008205838,0.00001795701,0.00006788445,0.00005549991,0.00005831293],"domain_scores_gemma":[0.9991608,0.0005420868,0.00008000567,0.00005759647,0.0001102011,0.00004934876],"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":[0.0001219224,0.00007000947,0.000637937,0.00007117058,0.00003086317,0.00003009921,0.00002062126,0.937642,0.001606553,0.01187629,0.0006271065,0.04726536],"study_design_scores_gemma":[0.000005461901,0.00001697836,0.00004462393,0.000002572943,0.000002769303,0.000002259948,0.000001031843,0.9973907,0.0001975361,0.002246253,0.00008823422,0.000001531176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.043066,0.001058307,0.9507607,0.0006742846,0.0001112978,0.00003919838,0.00006153999,0.0005175279,0.003711122],"genre_scores_gemma":[0.9641996,0.0002833823,0.03335486,0.0001555144,0.00004212954,0.00006212162,0.00004934088,0.00002077352,0.001832158],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006007318,"threshold_uncertainty_score":0.01194471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006951079625807076,"score_gpt":0.1974164743303396,"score_spread":0.1904653947045325,"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."}}