{"id":"W4309534481","doi":"10.1371/journal.pone.0277813","title":"Effects analysis of reward functions on reinforcement learning for traffic signal control","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Traffic control and management","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Korean National Police Agency","keywords":"Reinforcement learning; Computer science; Intersection (aeronautics); Scalability; Traffic flow (computer networking); Signal timing; Simulation; Traffic signal; Real-time computing; Artificial intelligence; Transport engineering; Computer network; 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":[0.003256299,0.001237111,0.0008568533,0.0004508138,0.0003557705,0.0007972987,0.0007236828,0.0008694499,0.001944716],"category_scores_gemma":[0.01153449,0.0003027811,0.0005385798,0.0002000485,0.0009202413,0.0009755414,0.0008600623,0.001269519,0.0001528947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001170372,"about_ca_system_score_gemma":0.001160928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003953897,"about_ca_topic_score_gemma":0.001619505,"domain_scores_codex":[0.9986583,0.0006441457,0.00004867869,0.0001679835,0.0002104156,0.0002704567],"domain_scores_gemma":[0.9924927,0.005591565,0.0005712904,0.0002071874,0.0008711969,0.0002660487],"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":[0.0002931433,0.0001098897,0.0007631045,0.00007925287,0.00003010361,0.00006895953,0.000036493,0.9781685,0.0017479,0.006993418,0.0001759147,0.01153325],"study_design_scores_gemma":[0.00001393985,0.0001172092,0.000175338,0.000004661634,0.00001126037,0.000008061289,0.000005450381,0.9982178,0.0004508429,0.0009279187,0.0000634303,0.000004004753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2445534,0.0006943141,0.7462958,0.0004728092,0.00008603961,0.0001391473,0.00004612841,0.0004621461,0.007250176],"genre_scores_gemma":[0.9916003,0.00009339032,0.007566406,0.00003135463,0.000008577521,0.00004370563,0.000009936783,0.00001385916,0.0006325636],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003953897,"threshold_uncertainty_score":0.01722121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01170924927935002,"score_gpt":0.1779327342918116,"score_spread":0.1662234850124616,"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."}}