{"id":"W2097152070","doi":"10.1109/itsc.2007.4357719","title":"Urban Traffic Control Based on Learning Agents","year":2007,"lang":"en","type":"article","venue":"","topic":"Traffic control and management","field":"Engineering","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Traffic flow (computer networking); Controller (irrigation); Control (management); Traffic signal; Intelligent transportation system; Reinforcement learning; Distributed computing; Artificial intelligence; Real-time computing; Computer network; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001963785,0.0001049173,0.0001000652,0.00009086766,0.00003489017,0.00001816546,0.00006920305,0.00003341074,0.0002516746],"category_scores_gemma":[0.000009391288,0.00009483735,0.00005311033,0.00007552998,0.000006350789,0.00002544671,0.000003532098,0.0001148405,0.0001627929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003812557,"about_ca_system_score_gemma":0.000002660352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002112092,"about_ca_topic_score_gemma":0.00001987944,"domain_scores_codex":[0.9993733,0.000008347983,0.000126124,0.0001068886,0.0001300768,0.0002553076],"domain_scores_gemma":[0.9997439,0.00006195622,0.000009349489,0.0001065264,0.000007808869,0.00007043181],"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":[0.00001984983,0.00002433365,0.0001161487,0.00001052831,0.0000226037,0.00001414005,0.00003332939,0.9155632,0.00007407723,0.0002067064,0.009302136,0.0746129],"study_design_scores_gemma":[0.001501468,0.00005960859,0.01262347,0.000007505406,0.00001412337,2.064564e-7,0.00003522705,0.835701,0.00003099265,7.465869e-7,0.1498986,0.0001270493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.206635,0.0001531807,0.3554202,0.000383936,0.001141523,0.0006837883,0.000002404111,0.00438497,0.4311951],"genre_scores_gemma":[0.9975792,0.000001821512,0.0001211476,0.0003767998,0.00008278114,0.000006392693,0.000002875511,0.00001986196,0.001809161],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7909442,"threshold_uncertainty_score":0.3867355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005686180185488333,"score_gpt":0.1883398676459957,"score_spread":0.1826536874605074,"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."}}