{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001216616,0.0008446291,0.001043297,0.0003959496,0.0002173634,0.0006379183,0.0008146751,0.000788471,0.001743339],"category_scores_gemma":[0.003412884,0.0002830628,0.0004058515,0.0003364939,0.001016072,0.0004926689,0.0006335274,0.001282983,0.0001835928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001031333,"about_ca_system_score_gemma":0.001207398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01203922,"about_ca_topic_score_gemma":0.004749884,"domain_scores_codex":[0.9995671,0.0001582106,0.00001724907,0.00007827784,0.00009771329,0.00008138373],"domain_scores_gemma":[0.9980155,0.001355118,0.0001945956,0.0000646058,0.000284101,0.00008600017],"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":[0.00003167327,0.00002312003,0.0001610818,0.00002560741,0.00001168593,0.0000157106,0.00000972544,0.9904097,0.000347591,0.002272548,0.0001981154,0.006493456],"study_design_scores_gemma":[0.000004762725,0.00001625769,0.00002380227,0.000001347255,0.000001558821,0.000001342932,8.803033e-7,0.9991208,0.0000574659,0.0007194097,0.000051132,0.000001237812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04974576,0.0008857849,0.9443734,0.0003535668,0.00007978749,0.00004359478,0.00004205207,0.0005672122,0.003908817],"genre_scores_gemma":[0.9702691,0.0001984357,0.02742805,0.00008544044,0.00003154475,0.00007534952,0.00005204949,0.00003484796,0.001825149],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01203922,"threshold_uncertainty_score":0.0239383,"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."}}