{"id":"W3216596730","doi":"10.1155/2021/6616702","title":"Adaptive Optimization of Traffic Signal Timing via Deep Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Traffic control and management","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Reinforcement learning; Queue; Traffic flow (computer networking); Computer science; Intersection (aeronautics); Real-time computing; Traffic optimization; Signal timing; Convergence (economics); Traffic signal; Scheme (mathematics); Traffic congestion; Simulation; Floating car data; Engineering; Artificial intelligence; Computer network; Transport engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006369711,0.0007061959,0.0006875906,0.0003259075,0.000224189,0.0005407038,0.0008144664,0.0006348474,0.001103874],"category_scores_gemma":[0.001979751,0.000370094,0.0003679535,0.0002702964,0.0005742394,0.0006478655,0.0006704761,0.001145957,0.0001498275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009283649,"about_ca_system_score_gemma":0.00133359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008885348,"about_ca_topic_score_gemma":0.007733613,"domain_scores_codex":[0.9997165,0.00006059585,0.00001157271,0.00007884136,0.00006023241,0.00007238257],"domain_scores_gemma":[0.9994673,0.0002456447,0.00009153145,0.00002688429,0.0001160723,0.00005261656],"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":[0.00003887889,0.0000406717,0.0006703291,0.00002047155,0.00001382487,0.00002163138,0.00001471894,0.9799738,0.001001455,0.002250343,0.0004302351,0.01552374],"study_design_scores_gemma":[0.000002670109,0.000006030185,0.00003139952,8.443593e-7,0.000001440318,0.000001424312,8.043996e-7,0.9993976,0.00009396558,0.0004245487,0.00003833594,9.021238e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.081163,0.0003591163,0.9133277,0.0003350436,0.00008338702,0.00004088332,0.00006921167,0.0006972162,0.003924396],"genre_scores_gemma":[0.9756809,0.00008736835,0.0227048,0.00008364778,0.00001957329,0.00004519311,0.00006414813,0.00002644183,0.001287853],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008885348,"threshold_uncertainty_score":0.01766729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006340755321841161,"score_gpt":0.1981025779935188,"score_spread":0.1917618226716776,"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."}}