{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001488143,0.0009294535,0.001138186,0.0004058867,0.0002967157,0.0007440293,0.001233514,0.0011571,0.00215851],"category_scores_gemma":[0.003241363,0.0004483923,0.0004830329,0.0003600573,0.0009127068,0.0008404299,0.001046511,0.001895583,0.0002547982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001388343,"about_ca_system_score_gemma":0.001850263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0076689,"about_ca_topic_score_gemma":0.006476559,"domain_scores_codex":[0.9994299,0.0001824677,0.00003115661,0.0001152829,0.0001341856,0.000107007],"domain_scores_gemma":[0.9986999,0.0007658439,0.0001425549,0.00006028006,0.0002625886,0.00006876195],"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":[0.00004169175,0.00003260508,0.0003180821,0.00004297648,0.00002157098,0.00003322143,0.00002657664,0.9759316,0.0006619842,0.006718935,0.0004106721,0.0157601],"study_design_scores_gemma":[0.000005174755,0.00001271379,0.00002029336,0.000002369259,0.000002864071,0.000002221381,0.000001167544,0.9982564,0.00009497643,0.001499436,0.0001008584,0.00000149168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01470646,0.0004527344,0.9821553,0.000279269,0.00004272457,0.00003814242,0.00003904031,0.0003146297,0.001971744],"genre_scores_gemma":[0.927229,0.000256696,0.06964123,0.0002488631,0.00004796986,0.0001591691,0.00009463647,0.00005373374,0.002268686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0076689,"threshold_uncertainty_score":0.01524854,"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."}}