{"id":"W4323262648","doi":"10.1016/j.knosys.2023.110440","title":"Deep reinforcement learning for traffic signal control with consistent state and reward design approach","year":2023,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Traffic control and management","field":"Engineering","cited_by":113,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"United Arab Emirates University","keywords":"Reinforcement learning; Computer science; Controller (irrigation); Key (lock); State (computer science); Convergence (economics); Traffic flow (computer networking); Traffic congestion; Artificial intelligence; Distributed computing; Computer security; Engineering; Transport engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007316188,0.000293954,0.0004316013,0.0002255652,0.0001564486,0.0001174251,0.000113498,0.00006449329,0.000005183805],"category_scores_gemma":[0.00001595087,0.0002475471,0.00008155414,0.0002528561,0.00004636528,0.00005665433,0.00001358358,0.0001363882,0.00004896565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001121831,"about_ca_system_score_gemma":0.00005147534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000508066,"about_ca_topic_score_gemma":0.00001630394,"domain_scores_codex":[0.9984562,0.0001108592,0.000392025,0.0003272793,0.0001973193,0.0005162907],"domain_scores_gemma":[0.9991506,0.0003343496,0.00006864154,0.0001918389,0.0001006451,0.0001538837],"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":[0.0001922476,0.00002742877,0.00002491806,0.0010863,0.0002605021,0.000007830183,0.0005385689,0.9878616,0.0001676834,0.0001018382,0.001418483,0.00831259],"study_design_scores_gemma":[0.004948614,0.0003841586,0.00008551799,0.0001328649,0.0001175721,0.000003782195,0.0004763242,0.9828539,0.00003333336,0.000001852182,0.01064288,0.0003191798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005877393,0.001599197,0.9872295,0.00002773611,0.0003169081,0.002561549,0.000003965074,0.0009742458,0.001409548],"genre_scores_gemma":[0.996433,0.00001763617,0.000417194,0.00001130595,0.00009721632,0.001370252,0.00003453336,0.00006936285,0.00154947],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9905556,"threshold_uncertainty_score":0.9999977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01785225752167014,"score_gpt":0.2013260996967499,"score_spread":0.1834738421750797,"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."}}