{"id":"W2791134267","doi":"10.1139/cjce-2017-0408","title":"Continuous residual reinforcement learning for traffic signal control optimization","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Traffic control and management","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; SIGNAL (programming language); Computer science; Controller (irrigation); Reinforcement; Adaptive control; Control theory (sociology); Residual; Feature (linguistics); Control (management); Artificial intelligence; Engineering; Algorithm","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002842356,0.0001548859,0.0002427236,0.0003359817,0.00008431185,0.00007015219,0.0001490213,0.00006013628,0.0001892346],"category_scores_gemma":[0.00007220932,0.0001657109,0.00009262106,0.0001128976,0.00002216557,0.000145675,0.000003204563,0.0001746641,0.000003457369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001628537,"about_ca_system_score_gemma":0.0001215633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002960934,"about_ca_topic_score_gemma":0.006284926,"domain_scores_codex":[0.9990074,0.000008524816,0.0003806897,0.00008250293,0.0001226947,0.0003982065],"domain_scores_gemma":[0.9992983,0.00005442221,0.00007083968,0.00007706128,0.000169785,0.000329604],"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":[0.00001408325,0.000001745745,0.00001133558,0.00003687225,0.0001181552,0.00001603231,0.0002103528,0.9933417,0.0001615686,0.0001206204,0.002821456,0.003146047],"study_design_scores_gemma":[0.001395364,0.0002628478,0.0001267081,0.00008067214,0.00006546034,0.00002281594,0.00005683041,0.949324,0.00005175115,0.000003057184,0.04843016,0.0001803563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006613717,0.0006476,0.9898558,0.0001157699,0.001043109,0.0002557382,0.000003958269,0.0001036755,0.001360677],"genre_scores_gemma":[0.9980107,0.00001308055,0.0009715586,0.00003467023,0.000798512,0.0000103006,0.000003907558,0.00004270621,0.0001145864],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.991397,"threshold_uncertainty_score":0.6757495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00454553229499981,"score_gpt":0.1654531979164221,"score_spread":0.1609076656214223,"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."}}