{"id":"W4240397898","doi":"10.5383/jttm.01.01.003","title":"Evaluating Reinforcement Learning State Representations for Adaptive Traffic Signal Control","year":2019,"lang":"en","type":"article","venue":"International Journal of Traffic and Transportation Management","topic":"Traffic control and management","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Reinforcement learning; Computer science; Asynchronous communication; Artificial neural network; State (computer science); SIGNAL (programming language); Artificial intelligence; Real-time computing; Machine learning; Control engineering; Engineering; Algorithm; Telecommunications","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0003957303,0.0001561282,0.0002130303,0.0002644897,0.00004786555,0.00006268907,0.0001725134,0.00002739782,0.0001014897],"category_scores_gemma":[0.000004445258,0.0001524004,0.0001481464,0.00007334009,0.00001865621,0.0002605077,0.00000432989,0.0001329143,0.000006710296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006992807,"about_ca_system_score_gemma":0.00001514535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001393239,"about_ca_topic_score_gemma":0.000009749664,"domain_scores_codex":[0.9985068,0.00002258837,0.0006355916,0.0001592398,0.0005006156,0.0001751173],"domain_scores_gemma":[0.9993085,0.0001018608,0.0002154164,0.00006405736,0.0002414868,0.00006864664],"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":[0.0003024007,0.00003287977,0.00005824299,0.00006119616,0.0008758589,0.00001686337,0.0006237175,0.8562399,0.00005947433,0.001369544,0.0001385852,0.1402214],"study_design_scores_gemma":[0.00774888,0.0005097263,0.009164354,0.0001253384,0.0003091433,0.000006081784,0.00133303,0.974907,0.0000215688,0.0001052734,0.005541132,0.000228458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7093536,0.000328288,0.2866805,0.0003590721,0.001195068,0.001097376,0.00002610283,0.0001235509,0.0008363992],"genre_scores_gemma":[0.9964957,0.000236691,0.002516966,0.00006117753,0.00008758733,0.00004205474,0.00004009455,0.00002174789,0.0004979954],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2871421,"threshold_uncertainty_score":0.6214708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01352449497375283,"score_gpt":0.2651455425027036,"score_spread":0.2516210475289508,"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."}}