{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002059468,0.0002103883,0.000236684,0.00008462597,0.0001938749,0.00005529383,0.0001268254,0.00005770467,0.0004326807],"category_scores_gemma":[0.00002128085,0.0001894965,0.0001217441,0.00008453985,0.00004276844,0.0001204483,0.00002452262,0.0001852263,0.0001091881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006828947,"about_ca_system_score_gemma":0.000007625751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007307575,"about_ca_topic_score_gemma":0.00006088746,"domain_scores_codex":[0.9988701,0.000024006,0.0002591656,0.0002204671,0.0001638163,0.0004623827],"domain_scores_gemma":[0.9995895,0.0001034329,0.00003967803,0.0001080947,0.00006199506,0.00009730749],"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":[0.0001442037,0.000005883536,0.000009715766,0.00002264758,0.0001573248,0.000001385681,0.0003627205,0.9198006,0.0002215906,0.001449339,0.0005917252,0.07723287],"study_design_scores_gemma":[0.002038817,0.0007352876,0.0002141534,0.00001586633,0.00006531043,8.22792e-7,0.0003814201,0.926624,0.00008246221,0.00001338,0.06958315,0.0002453401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00466613,0.0001224852,0.9755818,0.0001078499,0.0002485806,0.0006406574,6.101999e-7,0.0009865604,0.0176453],"genre_scores_gemma":[0.9945306,0.00001638523,0.001013636,0.00009707429,0.0003533866,0.000150456,0.00001118292,0.00004356834,0.003783719],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9898645,"threshold_uncertainty_score":0.7727441,"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."}}