{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001234507,0.0001372364,0.0002255722,0.00008573048,0.00002931266,0.00001800707,0.00009340508,0.00003546202,0.0002862702],"category_scores_gemma":[0.000004441503,0.0001088048,0.00005379079,0.00009509717,0.00001736777,0.0000742933,0.00001586021,0.000104096,0.00001806949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003858734,"about_ca_system_score_gemma":0.000007363829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003503566,"about_ca_topic_score_gemma":0.00005306861,"domain_scores_codex":[0.9991902,0.0000155152,0.0002206881,0.0001325122,0.0002091697,0.000231944],"domain_scores_gemma":[0.999685,0.0000533638,0.00004331769,0.00014135,0.00002988642,0.00004709866],"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":[0.00007686886,0.00001035234,0.0008318425,0.00007834256,0.0001250563,0.000002089047,0.0003680438,0.9872748,0.003771885,0.00005904075,0.00001880874,0.007382911],"study_design_scores_gemma":[0.002366562,0.0001756592,0.001195188,0.00003955469,0.00004534558,0.00000164191,0.0004828376,0.9910479,0.0002566412,5.614836e-7,0.004232109,0.0001560332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8780782,0.0001388253,0.1137621,0.00001341015,0.00007028299,0.0003753308,4.205089e-7,0.000305453,0.007256001],"genre_scores_gemma":[0.998593,0.000005425446,0.0007219386,0.00002030587,0.00002986992,0.000008204685,0.000002018201,0.00002433575,0.0005948454],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1205149,"threshold_uncertainty_score":0.443693,"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."}}