{"id":"W4285127047","doi":"10.1109/tits.2022.3179893","title":"Adaptive Traffic Signal Control With Deep Reinforcement Learning and High Dimensional Sensory Inputs: Case Study and Comprehensive Sensitivity Analyses","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Traffic control and management","field":"Engineering","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Sensitivity (control systems); Computer science; Sensory system; SIGNAL (programming language); Adaptive control; Control (management); Artificial intelligence; Machine learning; Engineering; Neuroscience; Psychology; Electronic 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":[0.001345725,0.000904689,0.0006387971,0.0006207296,0.0003433425,0.0006289168,0.0006626021,0.00140241,0.002104937],"category_scores_gemma":[0.003725717,0.0003337923,0.0008067787,0.0003372572,0.0009336896,0.000652457,0.00109659,0.001212201,0.00008287011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001446716,"about_ca_system_score_gemma":0.0005725458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01732956,"about_ca_topic_score_gemma":0.01002061,"domain_scores_codex":[0.9996027,0.000136353,0.00001737539,0.000056333,0.00007488355,0.00011237],"domain_scores_gemma":[0.9958288,0.003452014,0.0002083853,0.0001114988,0.0003085617,0.00009082683],"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":[0.00005693515,0.00004392015,0.0005681993,0.00004347135,0.00001716264,0.00009676694,0.00001141008,0.9964368,0.0003748868,0.00088925,0.0001490885,0.001312092],"study_design_scores_gemma":[0.00001068909,0.00004352492,0.000283423,0.000003490756,0.000006446161,0.000009335176,0.00001024678,0.9986024,0.0003178076,0.0006544258,0.00005408315,0.000004089344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8620828,0.001279318,0.1210587,0.0009627065,0.00006699797,0.0001904144,0.0005643931,0.0003723759,0.01342222],"genre_scores_gemma":[0.9969903,0.00005753382,0.002178847,0.00002592938,0.000003518077,0.0000307581,0.0000526279,0.000007158114,0.0006532952],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01732956,"threshold_uncertainty_score":0.03445739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02320251107494644,"score_gpt":0.241518189492159,"score_spread":0.2183156784172125,"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."}}