{"id":"W2991396018","doi":"10.1145/3345860.3361522","title":"Traffic Signal Control Using Deep Reinforcement Learning with Multiple Resources of Rewards","year":2019,"lang":"en","type":"article","venue":"","topic":"Traffic control and management","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Queue; Frame (networking); Control (management); SIGNAL (programming language); Traffic signal; Artificial intelligence; Real-time computing; Computer network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001327673,0.001139116,0.001165397,0.0004856125,0.0003605626,0.0009208021,0.001508436,0.001040684,0.001692958],"category_scores_gemma":[0.003172064,0.0004664782,0.0004819374,0.0003585014,0.0008275554,0.00109223,0.001013194,0.001987784,0.0002509273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001446155,"about_ca_system_score_gemma":0.001624135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01130971,"about_ca_topic_score_gemma":0.01069184,"domain_scores_codex":[0.9994169,0.0001587526,0.00002895803,0.0001619871,0.0001137605,0.0001195607],"domain_scores_gemma":[0.9987193,0.0006260613,0.0001786118,0.00007566385,0.0002733224,0.0001269962],"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":[0.0000712903,0.0001050934,0.0009259493,0.00003273965,0.00003520614,0.00004741233,0.00003241709,0.9568782,0.00101715,0.002827565,0.0008704049,0.03715653],"study_design_scores_gemma":[0.000005190158,0.00001191516,0.00003031997,0.000001659029,0.000002479495,0.000002287319,0.000001530716,0.9989512,0.0001064065,0.000822975,0.00006224939,0.000001839707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06175403,0.0005120604,0.9318726,0.0005419554,0.0001253455,0.00007751693,0.00008357282,0.001603722,0.003429297],"genre_scores_gemma":[0.9577084,0.00009297789,0.0401393,0.0001827117,0.000041543,0.00007273939,0.00008974248,0.00005044016,0.001622058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01130971,"threshold_uncertainty_score":0.02248776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004619129280543074,"score_gpt":0.1705126855282307,"score_spread":0.1658935562476876,"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."}}